@huggingface/transformers 3.1.0 → 3.1.2

package/dist/transformers.mjs

@@ -55,10 +55,10 @@ module.exports = __WEBPACK_EXTERNAL_MODULE_url__;
 
 /***/ }),
 
-/***/ "?cb4d":
-/*!*************************************!*\
-  !*** #onnxruntime-webgpu (ignored) ***!
-  \*************************************/
+/***/ "?8b6b":
+/*!*********************************!*\
+  !*** onnxruntime-web (ignored) ***!
+  \*********************************/
 /***/ (() => {
 
 /* (ignored) */
@@ -3871,7 +3871,7 @@ const version = '1.20.1';
   \******************************/
 /***/ ((__unused_webpack___webpack_module__, __webpack_exports__, __webpack_require__) => {
 
-var _onnxruntime_webgpu__WEBPACK_IMPORTED_MODULE_2___namespace_cache;
+var onnxruntime_web__WEBPACK_IMPORTED_MODULE_2___namespace_cache;
 __webpack_require__.r(__webpack_exports__);
 /* harmony export */ __webpack_require__.d(__webpack_exports__, {
 /* harmony export */   Tensor: () => (/* reexport safe */ onnxruntime_common__WEBPACK_IMPORTED_MODULE_3__.Tensor),
@@ -3882,7 +3882,7 @@ __webpack_require__.r(__webpack_exports__);
 /* harmony export */ });
 /* harmony import */ var _env_js__WEBPACK_IMPORTED_MODULE_0__ = __webpack_require__(/*! ../env.js */ "./src/env.js");
 /* harmony import */ var onnxruntime_node__WEBPACK_IMPORTED_MODULE_1__ = __webpack_require__(/*! onnxruntime-node */ "onnxruntime-node");
-/* harmony import */ var _onnxruntime_webgpu__WEBPACK_IMPORTED_MODULE_2__ = __webpack_require__(/*! #onnxruntime-webgpu */ "?cb4d");
+/* harmony import */ var onnxruntime_web__WEBPACK_IMPORTED_MODULE_2__ = __webpack_require__(/*! onnxruntime-web */ "?8b6b");
 /* harmony import */ var onnxruntime_common__WEBPACK_IMPORTED_MODULE_3__ = __webpack_require__(/*! onnxruntime-common */ "./node_modules/onnxruntime-common/dist/esm/index.js");
 /**
  * @file Handler file for choosing the correct version of ONNX Runtime, based on the environment.
@@ -3908,11 +3908,6 @@ __webpack_require__.r(__webpack_exports__);
 // In either case, we select the default export if it exists, otherwise we use the named export.
 
 
-// Use subpath-imports to ensure Node.js and browser interoperability.
-// See package.json and https://nodejs.org/api/packages.html#subpath-imports
-// for more information.
-// @ts-ignore
-
 
 
 
@@ -3954,7 +3949,7 @@ if (ORT_SYMBOL in globalThis) {
 } else if (_env_js__WEBPACK_IMPORTED_MODULE_0__.apis.IS_NODE_ENV) {
     ONNX = onnxruntime_node__WEBPACK_IMPORTED_MODULE_1__["default"] ?? onnxruntime_node__WEBPACK_IMPORTED_MODULE_1__;
 
-    // Updated as of ONNX Runtime 1.18.0
+    // Updated as of ONNX Runtime 1.20.1
     // The following table lists the supported versions of ONNX Runtime Node.js binding provided with pre-built binaries.
     // | EPs/Platforms | Windows x64 | Windows arm64 | Linux x64         | Linux arm64 | MacOS x64 | MacOS arm64 |
     // | ------------- | ----------- | ------------- | ----------------- | ----------- | --------- | ----------- |
@@ -3977,7 +3972,7 @@ if (ORT_SYMBOL in globalThis) {
     supportedDevices.push('cpu');
     defaultDevices = ['cpu'];
 } else {
-    ONNX = /*#__PURE__*/ (_onnxruntime_webgpu__WEBPACK_IMPORTED_MODULE_2___namespace_cache || (_onnxruntime_webgpu__WEBPACK_IMPORTED_MODULE_2___namespace_cache = __webpack_require__.t(_onnxruntime_webgpu__WEBPACK_IMPORTED_MODULE_2__, 2)));
+    ONNX = /*#__PURE__*/ (onnxruntime_web__WEBPACK_IMPORTED_MODULE_2___namespace_cache || (onnxruntime_web__WEBPACK_IMPORTED_MODULE_2___namespace_cache = __webpack_require__.t(onnxruntime_web__WEBPACK_IMPORTED_MODULE_2__, 2)));
 
     if (_env_js__WEBPACK_IMPORTED_MODULE_0__.apis.IS_WEBNN_AVAILABLE) {
         // TODO: Only push supported providers (depending on available hardware)
@@ -5533,6 +5528,7 @@ function getNormalizedConfig(config) {
         case 'paligemma':
         case 'florence2':
         case 'llava_onevision':
+        case 'idefics3':
             init_normalized_config = getNormalizedConfig(config.text_config);
             break;
         case 'moondream1':
@@ -5567,6 +5563,7 @@ function getNormalizedConfig(config) {
             break;
         case 'llama':
         case 'olmo':
+        case 'olmo2':
         case 'mobilellm':
         case 'granite':
         case 'cohere':
@@ -5846,7 +5843,7 @@ class AutoConfig {
  * See https://onnxruntime.ai/docs/tutorials/web/env-flags-and-session-options.html#freedimensionoverrides
  * for more information.
  * @property {import('./utils/devices.js').DeviceType} [device] The default device to use for the model.
- * @property {import('./utils/dtypes.js').DataType} [dtype] The default data type to use for the model.
+ * @property {import('./utils/dtypes.js').DataType|Record<string, import('./utils/dtypes.js').DataType>} [dtype] The default data type to use for the model.
  * @property {boolean|Record<string, boolean>} [use_external_data_format=false] Whether to load the model using the external data format (used for models >= 2GB in size).
  */
 
@@ -5895,12 +5892,12 @@ __webpack_require__.r(__webpack_exports__);
 
 
 
-const VERSION = '3.1.0';
+const VERSION = '3.1.2';
 
 // Check if various APIs are available (depends on environment)
-const IS_BROWSER_ENV = typeof self !== 'undefined';
-const IS_WEBWORKER_ENV = IS_BROWSER_ENV && self.constructor.name === 'DedicatedWorkerGlobalScope';
-const IS_WEB_CACHE_AVAILABLE = IS_BROWSER_ENV && 'caches' in self;
+const IS_BROWSER_ENV = typeof window !== "undefined" && typeof window.document !== "undefined";
+const IS_WEBWORKER_ENV = typeof self !== "undefined"  && self.constructor?.name === 'DedicatedWorkerGlobalScope';
+const IS_WEB_CACHE_AVAILABLE = typeof self !== "undefined" && 'caches' in self;
 const IS_WEBGPU_AVAILABLE = typeof navigator !== 'undefined' && 'gpu' in navigator;
 const IS_WEBNN_AVAILABLE = typeof navigator !== 'undefined' && 'ml' in navigator;
 
@@ -5913,7 +5910,7 @@ const IS_PATH_AVAILABLE = !isEmpty(path__WEBPACK_IMPORTED_MODULE_1__["default"])
  * A read-only object containing information about the APIs available in the current environment.
  */
 const apis = Object.freeze({
-    /** Whether we are running in a browser environment */
+    /** Whether we are running in a browser environment (and not a web worker) */
     IS_BROWSER_ENV,
 
     /** Whether we are running in a web worker environment */
@@ -6006,7 +6003,7 @@ const env = {
     remoteHost: 'https://huggingface.co/',
     remotePathTemplate: '{model}/resolve/{revision}/',
 
-    allowLocalModels: !IS_BROWSER_ENV,
+    allowLocalModels: !(IS_BROWSER_ENV || IS_WEBWORKER_ENV),
     localModelPath: localModelPath,
     useFS: IS_FS_AVAILABLE,
 
@@ -6306,6 +6303,13 @@ class GenerationConfig {
      */
     suppress_tokens = null;
 
+    /**
+     * A streamer that will be used to stream the generation.
+     * @type {import('./streamers.js').TextStreamer}
+     * @default null
+     */
+    streamer = null;
+
     /**
      * A list of tokens that will be suppressed at the beginning of the generation.
      * The `SuppressBeginTokens` logit processor will set their log probs to `-inf` so that they are not sampled.
@@ -6611,7 +6615,7 @@ class ForcedBOSTokenLogitsProcessor extends LogitsProcessor {
      * Apply the BOS token forcing to the logits.
      * @param {bigint[][]} input_ids The input IDs.
      * @param {Tensor} logits The logits.
-     * @returns {Object} The logits with BOS token forcing.
+     * @returns {Tensor} The logits with BOS token forcing.
      */
     _call(input_ids, logits) {
         for (let i = 0; i < input_ids.length; ++i) {
@@ -6681,7 +6685,7 @@ class SuppressTokensAtBeginLogitsProcessor extends LogitsProcessor {
      * Apply the BOS token forcing to the logits.
      * @param {bigint[][]} input_ids The input IDs.
      * @param {Tensor} logits The logits.
-     * @returns {Object} The logits with BOS token forcing.
+     * @returns {Tensor} The logits with BOS token forcing.
      */
     _call(input_ids, logits) {
         for (let i = 0; i < input_ids.length; ++i) {
@@ -6851,7 +6855,7 @@ class NoRepeatNGramLogitsProcessor extends LogitsProcessor {
      * Apply the no-repeat-ngram processor to the logits.
      * @param {bigint[][]} input_ids The input IDs.
      * @param {Tensor} logits The logits.
-     * @returns {Object} The logits with no-repeat-ngram processing.
+     * @returns {Tensor} The logits with no-repeat-ngram processing.
      */
     _call(input_ids, logits) {
         for (let i = 0; i < input_ids.length; ++i) {
@@ -6866,12 +6870,22 @@ class NoRepeatNGramLogitsProcessor extends LogitsProcessor {
 }
 
 /**
- * A logits processor that penalises repeated output tokens.
+ * A logits processor that prevents the repetition of previous tokens through a penalty.
+ * This penalty is applied at most once per token. Note that, for decoder-only models like most LLMs,
+ * the considered tokens include the prompt.
+ * 
+ * In the original [paper](https://arxiv.org/pdf/1909.05858.pdf), the authors suggest the use of a
+ * penalty of around 1.2 to achieve a good balance between truthful generation and lack of repetition.
+ * To penalize and reduce repetition, use `penalty` values above 1.0, where a higher value penalizes
+ * more strongly. To reward and encourage repetition, use `penalty` values between 0.0 and 1.0, where
+ * a lower value rewards more strongly.
  */
 class RepetitionPenaltyLogitsProcessor extends LogitsProcessor {
     /**
      * Create a RepetitionPenaltyLogitsProcessor.
-     * @param {number} penalty The penalty to apply for repeated tokens.
+     * @param {number} penalty The parameter for repetition penalty.
+     * - 1.0 means no penalty. Above 1.0 penalizes previously generated tokens.
+     * - Between 0.0 and 1.0 rewards previously generated tokens.
      */
     constructor(penalty) {
         super();
@@ -6882,16 +6896,12 @@ class RepetitionPenaltyLogitsProcessor extends LogitsProcessor {
      * Apply the repetition penalty to the logits.
      * @param {bigint[][]} input_ids The input IDs.
      * @param {Tensor} logits The logits.
-     * @returns {Object} The logits with repetition penalty processing.
+     * @returns {Tensor} The logits with repetition penalty processing.
      */
     _call(input_ids, logits) {
-        // Modify the logits corresponding to each element in `input_ids`.
-        // As a consequence, the logits corresponding to tokens that appear
-        // many times in the output will be penalised more.
-
         for (let i = 0; i < input_ids.length; ++i) {
             const batch_logits_data = /** @type {Float32Array} */(logits[i].data);
-            for (const input_id of input_ids[i]) {
+            for (const input_id of new Set(input_ids[i])) {
                 const token = Number(input_id);
                 if (batch_logits_data[token] < 0) {
                     batch_logits_data[token] *= this.penalty;
@@ -6924,7 +6934,7 @@ class MinLengthLogitsProcessor extends LogitsProcessor {
      * Apply logit processor.
      * @param {bigint[][]} input_ids The input IDs.
      * @param {Tensor} logits The logits.
-     * @returns {Object} The processed logits.
+     * @returns {Tensor} The processed logits.
      */
     _call(input_ids, logits) {
         for (let i = 0; i < input_ids.length; ++i) {
@@ -6962,7 +6972,7 @@ class MinNewTokensLengthLogitsProcessor extends LogitsProcessor {
      * Apply logit processor.
      * @param {bigint[][]} input_ids The input IDs.
      * @param {Tensor} logits The logits.
-     * @returns {Object} The processed logits.
+     * @returns {Tensor} The processed logits.
      */
     _call(input_ids, logits) {
         for (let i = 0; i < input_ids.length; ++i) {
@@ -6995,7 +7005,7 @@ class NoBadWordsLogitsProcessor extends LogitsProcessor {
      * Apply logit processor.
      * @param {bigint[][]} input_ids The input IDs.
      * @param {Tensor} logits The logits.
-     * @returns {Object} The processed logits.
+     * @returns {Tensor} The processed logits.
      */
     _call(input_ids, logits) {
         for (let i = 0; i < input_ids.length; ++i) {
@@ -7056,7 +7066,7 @@ class ClassifierFreeGuidanceLogitsProcessor extends LogitsProcessor {
      * Apply logit processor.
      * @param {bigint[][]} input_ids The input IDs.
      * @param {Tensor} logits The logits.
-     * @returns {Object} The processed logits.
+     * @returns {Tensor} The processed logits.
      */
     _call(input_ids, logits) {
         if (logits.dims[0] !== 2 * input_ids.length) {
@@ -7110,7 +7120,7 @@ class TemperatureLogitsWarper extends LogitsWarper {
      * Apply logit warper.
      * @param {bigint[][]} input_ids The input IDs.
      * @param {Tensor} logits The logits.
-     * @returns {Object} The processed logits.
+     * @returns {Tensor} The processed logits.
      */
     _call(input_ids, logits) {
         const batch_logits_data = /** @type {Float32Array} */(logits.data);
@@ -7625,7 +7635,12 @@ const stdout_write = _env_js__WEBPACK_IMPORTED_MODULE_2__.apis.IS_PROCESS_AVAILA
 class TextStreamer extends BaseStreamer {
     /**
      * 
-     * @param {import('../tokenizers.js').PreTrainedTokenizer} tokenizer 
+     * @param {import('../tokenizers.js').PreTrainedTokenizer} tokenizer
+     * @param {Object} options
+     * @param {boolean} [options.skip_prompt=false] Whether to skip the prompt tokens
+     * @param {function(string): void} [options.callback_function=null] Function to call when a piece of text is ready to display
+     * @param {function(bigint[]): void} [options.token_callback_function=null] Function to call when a new token is generated
+     * @param {Object} [options.decode_kwargs={}] Additional keyword arguments to pass to the tokenizer's decode method
      */
     constructor(tokenizer, {
         skip_prompt = false,
@@ -7734,7 +7749,7 @@ class WhisperTextStreamer extends TextStreamer {
      * @param {Object} options
      * @param {boolean} [options.skip_prompt=false] Whether to skip the prompt tokens
      * @param {function(string): void} [options.callback_function=null] Function to call when a piece of text is ready to display
-     * @param {function(string): void} [options.token_callback_function=null] Function to call when a new token is generated
+     * @param {function(bigint[]): void} [options.token_callback_function=null] Function to call when a new token is generated
      * @param {function(number): void} [options.on_chunk_start=null] Function to call when a new chunk starts
      * @param {function(number): void} [options.on_chunk_end=null] Function to call when a chunk ends
      * @param {function(): void} [options.on_finalize=null] Function to call when the stream is finalized
@@ -8013,6 +8028,11 @@ __webpack_require__.r(__webpack_exports__);
 /* harmony export */   HubertForSequenceClassification: () => (/* binding */ HubertForSequenceClassification),
 /* harmony export */   HubertModel: () => (/* binding */ HubertModel),
 /* harmony export */   HubertPreTrainedModel: () => (/* binding */ HubertPreTrainedModel),
+/* harmony export */   IJepaForImageClassification: () => (/* binding */ IJepaForImageClassification),
+/* harmony export */   IJepaModel: () => (/* binding */ IJepaModel),
+/* harmony export */   IJepaPreTrainedModel: () => (/* binding */ IJepaPreTrainedModel),
+/* harmony export */   Idefics3ForConditionalGeneration: () => (/* binding */ Idefics3ForConditionalGeneration),
+/* harmony export */   Idefics3PreTrainedModel: () => (/* binding */ Idefics3PreTrainedModel),
 /* harmony export */   ImageMattingOutput: () => (/* binding */ ImageMattingOutput),
 /* harmony export */   JAISLMHeadModel: () => (/* binding */ JAISLMHeadModel),
 /* harmony export */   JAISModel: () => (/* binding */ JAISModel),
@@ -8102,6 +8122,9 @@ __webpack_require__.r(__webpack_exports__);
 /* harmony export */   OPTForCausalLM: () => (/* binding */ OPTForCausalLM),
 /* harmony export */   OPTModel: () => (/* binding */ OPTModel),
 /* harmony export */   OPTPreTrainedModel: () => (/* binding */ OPTPreTrainedModel),
+/* harmony export */   Olmo2ForCausalLM: () => (/* binding */ Olmo2ForCausalLM),
+/* harmony export */   Olmo2Model: () => (/* binding */ Olmo2Model),
+/* harmony export */   Olmo2PreTrainedModel: () => (/* binding */ Olmo2PreTrainedModel),
 /* harmony export */   OlmoForCausalLM: () => (/* binding */ OlmoForCausalLM),
 /* harmony export */   OlmoModel: () => (/* binding */ OlmoModel),
 /* harmony export */   OlmoPreTrainedModel: () => (/* binding */ OlmoPreTrainedModel),
@@ -8114,6 +8137,8 @@ __webpack_require__.r(__webpack_exports__);
 /* harmony export */   Owlv2ForObjectDetection: () => (/* binding */ Owlv2ForObjectDetection),
 /* harmony export */   Owlv2Model: () => (/* binding */ Owlv2Model),
 /* harmony export */   Owlv2PreTrainedModel: () => (/* binding */ Owlv2PreTrainedModel),
+/* harmony export */   PaliGemmaForConditionalGeneration: () => (/* binding */ PaliGemmaForConditionalGeneration),
+/* harmony export */   PaliGemmaPreTrainedModel: () => (/* binding */ PaliGemmaPreTrainedModel),
 /* harmony export */   PatchTSMixerForPrediction: () => (/* binding */ PatchTSMixerForPrediction),
 /* harmony export */   PatchTSMixerModel: () => (/* binding */ PatchTSMixerModel),
 /* harmony export */   PatchTSMixerPreTrainedModel: () => (/* binding */ PatchTSMixerPreTrainedModel),
@@ -8419,6 +8444,22 @@ async function getSession(pretrained_model_name_or_path, fileName, options) {
         }
     }
 
+    if (dtype === _utils_dtypes_js__WEBPACK_IMPORTED_MODULE_2__.DATA_TYPES.auto) {
+        // Try to choose the auto dtype based on the custom config
+        let config_dtype = custom_config.dtype;
+        if (typeof config_dtype !== 'string') {
+            config_dtype = config_dtype[fileName];
+        }
+
+        if (config_dtype && config_dtype !== _utils_dtypes_js__WEBPACK_IMPORTED_MODULE_2__.DATA_TYPES.auto && _utils_dtypes_js__WEBPACK_IMPORTED_MODULE_2__.DATA_TYPES.hasOwnProperty(config_dtype)) {
+            // Defined by the custom config, and is not "auto"
+            dtype = config_dtype;
+        } else {
+            // Choose default dtype based on device, falling back to fp32
+            dtype = _utils_dtypes_js__WEBPACK_IMPORTED_MODULE_2__.DEFAULT_DEVICE_DTYPE_MAPPING[selectedDevice] ?? _utils_dtypes_js__WEBPACK_IMPORTED_MODULE_2__.DATA_TYPES.fp32;
+        }
+    }
+
     const selectedDtype = /** @type {import("./utils/dtypes.js").DataType} */(dtype);
 
     if (!_utils_dtypes_js__WEBPACK_IMPORTED_MODULE_2__.DEFAULT_DTYPE_SUFFIX_MAPPING.hasOwnProperty(selectedDtype)) {
@@ -8624,9 +8665,17 @@ async function sessionRun(session, inputs) {
         output = replaceTensors(output);
         return output;
     } catch (e) {
+        // Error messages can be long (nested) and uninformative. For this reason,
+        // we apply minor formatting to show the most important information
+        const formatted = Object.fromEntries(Object.entries(checkedInputs)
+            .map(([k, { type, dims, data }]) => [k, {
+                // Extract these properties from the underlying ORT tensor
+                type, dims, data,
+            }]));
+
         // This usually occurs when the inputs are of the wrong type.
         console.error(`An error occurred during model execution: "${e}".`);
-        console.error('Inputs given to model:', checkedInputs)
+        console.error('Inputs given to model:', formatted);
         throw e;
     }
 }
@@ -8771,7 +8820,9 @@ async function decoderForward(self, model_inputs, is_encoder_decoder = false) {
         new_model_inputs.use_cache_branch = boolTensor(!!past_key_values);
     }
     if (session.inputNames.includes('position_ids') && new_model_inputs.attention_mask && !new_model_inputs.position_ids) {
-        new_model_inputs.position_ids = createPositionIds(new_model_inputs, past_key_values);
+        // NOTE: Handle a special case for paligemma models, where positions are 1-indexed
+        const start_index = self.config.model_type === 'paligemma' ? 1 : 0;
+        new_model_inputs.position_ids = createPositionIds(new_model_inputs, past_key_values, start_index);
     }
 
     // Unpack the `past_key_values` object into model inputs
@@ -8783,6 +8834,39 @@ async function decoderForward(self, model_inputs, is_encoder_decoder = false) {
 }
 
 
+
+function default_merge_input_ids_with_image_features({
+    image_token_id,
+    inputs_embeds,
+    image_features,
+    input_ids,
+    attention_mask,
+}) {
+    const image_tokens = input_ids.tolist().map(ids =>
+        ids.reduce((acc, x, idx) => {
+            if (x == image_token_id) acc.push(idx);
+            return acc;
+        }, [])
+    );
+    const n_image_tokens = image_tokens.reduce((acc, x) => acc + x.length, 0);
+    const n_image_features = image_features.dims[0];
+    if (n_image_tokens !== n_image_features) {
+        throw new Error(`Image features and image tokens do not match: tokens: ${n_image_tokens}, features ${n_image_features}`);
+    }
+
+    // Equivalent to performing a masked_scatter
+    let img = 0;
+    for (let i = 0; i < image_tokens.length; ++i) {
+        const tokens = image_tokens[i];
+        const embeds = inputs_embeds[i];
+        for (let j = 0; j < tokens.length; ++j) {
+            embeds[tokens[j]].data.set(image_features[img++].data)
+        }
+    }
+    return { inputs_embeds, attention_mask }
+}
+
+
 /**
  * Forward pass of an image-text-to-text model.
  * @param {Object} self The image-text-to-text model model.
@@ -8874,14 +8958,14 @@ async function imageTextToTextForward(self, {
  * @param {Tensor} attention_mask
  * @returns {{data: BigInt64Array, dims: number[]}}
  */
-function cumsum_masked_fill(attention_mask) {
+function cumsum_masked_fill(attention_mask, start_index = 0) {
     const [bz, seq_len] = attention_mask.dims;
     const attn_mask_data = attention_mask.data;
 
     const data = new BigInt64Array(attn_mask_data.length);
     for (let i = 0; i < bz; ++i) {
         const start = i * seq_len;
-        let sum = BigInt(0);
+        let sum = BigInt(start_index);
         for (let j = 0; j < seq_len; ++j) {
             const index = start + j;
             if (attn_mask_data[index] === 0n) {
@@ -8908,10 +8992,10 @@ function cumsum_masked_fill(attention_mask) {
  *     position_ids = position_ids[:, -input_ids.shape[1] :]
  * ```
  */
-function createPositionIds(model_inputs, past_key_values = null) {
+function createPositionIds(model_inputs, past_key_values = null, start_index = 0) {
     const { input_ids, inputs_embeds, attention_mask } = model_inputs;
 
-    const { data, dims } = cumsum_masked_fill(attention_mask);
+    const { data, dims } = cumsum_masked_fill(attention_mask, start_index);
     let position_ids = new _utils_tensor_js__WEBPACK_IMPORTED_MODULE_9__.Tensor('int64', data, dims);
     if (past_key_values) {
         const offset = -(input_ids ?? inputs_embeds).dims.at(1);
@@ -9250,7 +9334,10 @@ class PreTrainedModel extends _utils_generic_js__WEBPACK_IMPORTED_MODULE_3__.Cal
 
         } else { // should be MODEL_TYPES.EncoderOnly
             if (modelType !== MODEL_TYPES.EncoderOnly) {
-                console.warn(`Model type for '${modelName ?? config?.model_type}' not found, assuming encoder-only architecture. Please report this at ${_utils_constants_js__WEBPACK_IMPORTED_MODULE_6__.GITHUB_ISSUE_URL}.`)
+                const type = modelName ?? config?.model_type;
+                if (type !== 'custom') {
+                    console.warn(`Model type for '${type}' not found, assuming encoder-only architecture. Please report this at ${_utils_constants_js__WEBPACK_IMPORTED_MODULE_6__.GITHUB_ISSUE_URL}.`)
+                }
             }
             info = await Promise.all([
                 constructSessions(pretrained_model_name_or_path, {
@@ -9994,7 +10081,7 @@ class PreTrainedModel extends _utils_generic_js__WEBPACK_IMPORTED_MODULE_3__.Cal
             const dtype = session?.config?.kv_cache_dtype ?? 'float32';
             const empty = (dtype === 'float16') ? new Uint16Array() : [];
 
-            const batch_size = (decoderFeeds[this.main_input_name] ?? decoderFeeds.attention_mask).dims?.[0] ?? 1;
+            const batch_size = (decoderFeeds[this.main_input_name] ?? decoderFeeds.attention_mask)?.dims?.[0] ?? 1;
             const shapes = (0,_configs_js__WEBPACK_IMPORTED_MODULE_0__.getKeyValueShapes)(this.config, { batch_size });
 
             for (const name in shapes) {
@@ -11541,8 +11628,8 @@ class VisionEncoderDecoderModel extends PreTrainedModel {
 class LlavaPreTrainedModel extends PreTrainedModel {
     forward_params = [
         'input_ids',
-        'pixel_values',
         'attention_mask',
+        'pixel_values',
         'position_ids',
         'past_key_values',
     ];
@@ -11724,6 +11811,70 @@ class Florence2ForConditionalGeneration extends Florence2PreTrainedModel {
         return decoder_outputs;
     }
 }
+
+class PaliGemmaPreTrainedModel extends PreTrainedModel {
+    forward_params = [
+        'input_ids',
+        // 'inputs_embeds',
+        'attention_mask',
+        'pixel_values',
+        'position_ids',
+        'past_key_values',
+    ];
+}
+
+class PaliGemmaForConditionalGeneration extends PaliGemmaPreTrainedModel {
+    _merge_input_ids_with_image_features(kwargs) {
+        const vision_hidden_size = kwargs.image_features.dims.at(-1);
+        const reshaped_image_hidden_states = kwargs.image_features.view(-1, vision_hidden_size);
+
+        return default_merge_input_ids_with_image_features({
+            // @ts-ignore
+            image_token_id: this.config.image_token_index,
+            ...kwargs,
+            image_features: reshaped_image_hidden_states,
+        })
+    }
+}
+
+//////////////////////////////////////////////////
+// Idefics3 Models
+class Idefics3PreTrainedModel extends PreTrainedModel {
+    forward_params = [
+        'input_ids',
+        'attention_mask',
+        'pixel_values',
+        'pixel_attention_mask',
+        'position_ids',
+        'past_key_values',
+    ];
+}
+
+/**
+ * The LLAVA model which consists of a vision backbone and a language model.
+ */
+class Idefics3ForConditionalGeneration extends Idefics3PreTrainedModel {
+
+    async encode_image({ pixel_values, pixel_attention_mask }) {
+        const features = (await sessionRun(this.sessions['vision_encoder'], { pixel_values, pixel_attention_mask })).image_features;
+        return features;
+    }
+
+    _merge_input_ids_with_image_features(kwargs) {
+        const vision_hidden_size = kwargs.image_features.dims.at(-1);
+        const reshaped_image_hidden_states = kwargs.image_features.view(-1, vision_hidden_size);
+
+        return default_merge_input_ids_with_image_features({
+            // @ts-ignore
+            image_token_id: this.config.image_token_id,
+            ...kwargs,
+            image_features: reshaped_image_hidden_states,
+        })
+    }
+}
+//////////////////////////////////////////////////
+
+//////////////////////////////////////////////////
 class CLIPPreTrainedModel extends PreTrainedModel { }
 
 /**
@@ -12223,6 +12374,13 @@ class OlmoModel extends OlmoPreTrainedModel { }
 class OlmoForCausalLM extends OlmoPreTrainedModel { }
 //////////////////////////////////////////////////
 
+//////////////////////////////////////////////////
+// OLMo2 models
+class Olmo2PreTrainedModel extends PreTrainedModel { }
+class Olmo2Model extends Olmo2PreTrainedModel { }
+class Olmo2ForCausalLM extends Olmo2PreTrainedModel { }
+//////////////////////////////////////////////////
+
 
 //////////////////////////////////////////////////
 // Granite models
@@ -12517,36 +12675,12 @@ class Qwen2VLForConditionalGeneration extends Qwen2VLPreTrainedModel {
         return features;
     }
 
-    _merge_input_ids_with_image_features({
-        inputs_embeds,
-        image_features,
-        input_ids,
-        attention_mask,
-    }) {
-        // @ts-ignore
-        const { image_token_id } = this.config;
-        const image_tokens = input_ids.tolist().map(ids =>
-            ids.reduce((acc, x, idx) => {
-                if (x == image_token_id) acc.push(idx);
-                return acc;
-            }, [])
-        );
-        const n_image_tokens = image_tokens.reduce((acc, x) => acc + x.length, 0);
-        const n_image_features = image_features.dims[0];
-        if (n_image_tokens !== n_image_features) {
-            throw new Error(`Image features and image tokens do not match: tokens: ${n_image_tokens}, features ${n_image_features}`);
-        }
-
-        // Equivalent to performing a masked_scatter
-        let img = 0;
-        for (let i = 0; i < image_tokens.length; ++i) {
-            const tokens = image_tokens[i];
-            const embeds = inputs_embeds[i];
-            for (let j = 0; j < tokens.length; ++j) {
-                embeds[tokens[j]].data.set(image_features[img++].data)
-            }
-        }
-        return { inputs_embeds, attention_mask }
+    _merge_input_ids_with_image_features(kwargs) {
+        return default_merge_input_ids_with_image_features({
+            // @ts-ignore
+            image_token_id: this.config.image_token_id,
+            ...kwargs
+        })
     }
 
     prepare_inputs_for_generation(input_ids, model_inputs, generation_config) {
@@ -12663,6 +12797,20 @@ class ViTForImageClassification extends ViTPreTrainedModel {
 //////////////////////////////////////////////////
 
 
+//////////////////////////////////////////////////
+class IJepaPreTrainedModel extends PreTrainedModel { }
+class IJepaModel extends IJepaPreTrainedModel { }
+class IJepaForImageClassification extends IJepaPreTrainedModel {
+    /**
+     * @param {any} model_inputs
+     */
+    async _call(model_inputs) {
+        return new SequenceClassifierOutput(await super._call(model_inputs));
+    }
+}
+//////////////////////////////////////////////////
+
+
 //////////////////////////////////////////////////
 class VitPosePreTrainedModel extends PreTrainedModel { }
 
@@ -14933,6 +15081,7 @@ const MODEL_MAPPING_NAMES_ENCODER_ONLY = new Map([
     ['rt_detr', ['RTDetrModel', RTDetrModel]],
     ['table-transformer', ['TableTransformerModel', TableTransformerModel]],
     ['vit', ['ViTModel', ViTModel]],
+    ['ijepa', ['IJepaModel', IJepaModel]],
     ['pvt', ['PvtModel', PvtModel]],
     ['vit_msn', ['ViTMSNModel', ViTMSNModel]],
     ['vit_mae', ['ViTMAEModel', ViTMAEModel]],
@@ -14997,6 +15146,7 @@ const MODEL_MAPPING_NAMES_DECODER_ONLY = new Map([
     ['codegen', ['CodeGenModel', CodeGenModel]],
     ['llama', ['LlamaModel', LlamaModel]],
     ['olmo', ['OlmoModel', OlmoModel]],
+    ['olmo2', ['Olmo2Model', Olmo2Model]],
     ['mobilellm', ['MobileLLMModel', MobileLLMModel]],
     ['granite', ['GraniteModel', GraniteModel]],
     ['cohere', ['CohereModel', CohereModel]],
@@ -15088,6 +15238,7 @@ const MODEL_FOR_CAUSAL_LM_MAPPING_NAMES = new Map([
     ['codegen', ['CodeGenForCausalLM', CodeGenForCausalLM]],
     ['llama', ['LlamaForCausalLM', LlamaForCausalLM]],
     ['olmo', ['OlmoForCausalLM', OlmoForCausalLM]],
+    ['olmo2', ['Olmo2ForCausalLM', Olmo2ForCausalLM]],
     ['mobilellm', ['MobileLLMForCausalLM', MobileLLMForCausalLM]],
     ['granite', ['GraniteForCausalLM', GraniteForCausalLM]],
     ['cohere', ['CohereForCausalLM', CohereForCausalLM]],
@@ -15151,6 +15302,7 @@ const MODEL_FOR_QUESTION_ANSWERING_MAPPING_NAMES = new Map([
 
 const MODEL_FOR_VISION_2_SEQ_MAPPING_NAMES = new Map([
     ['vision-encoder-decoder', ['VisionEncoderDecoderModel', VisionEncoderDecoderModel]],
+    ['idefics3', ['Idefics3ForConditionalGeneration', Idefics3ForConditionalGeneration]],
 ]);
 
 const MODEL_FOR_IMAGE_TEXT_TO_TEXT_MAPPING_NAMES = new Map([
@@ -15159,6 +15311,8 @@ const MODEL_FOR_IMAGE_TEXT_TO_TEXT_MAPPING_NAMES = new Map([
     ['moondream1', ['Moondream1ForConditionalGeneration', Moondream1ForConditionalGeneration]],
     ['florence2', ['Florence2ForConditionalGeneration', Florence2ForConditionalGeneration]],
     ['qwen2-vl', ['Qwen2VLForConditionalGeneration', Qwen2VLForConditionalGeneration]],
+    ['idefics3', ['Idefics3ForConditionalGeneration', Idefics3ForConditionalGeneration]],
+    ['paligemma', ['PaliGemmaForConditionalGeneration', PaliGemmaForConditionalGeneration]],
 ]);
 
 const MODEL_FOR_DOCUMENT_QUESTION_ANSWERING_MAPPING_NAMES = new Map([
@@ -15167,6 +15321,7 @@ const MODEL_FOR_DOCUMENT_QUESTION_ANSWERING_MAPPING_NAMES = new Map([
 
 const MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES = new Map([
     ['vit', ['ViTForImageClassification', ViTForImageClassification]],
+    ['ijepa', ['IJepaForImageClassification', IJepaForImageClassification]],
     ['pvt', ['PvtForImageClassification', PvtForImageClassification]],
     ['vit_msn', ['ViTMSNForImageClassification', ViTMSNForImageClassification]],
     ['fastvit', ['FastViTForImageClassification', FastViTForImageClassification]],
@@ -16770,6 +16925,394 @@ __webpack_require__.r(__webpack_exports__);
 class GLPNFeatureExtractor extends _base_image_processors_utils_js__WEBPACK_IMPORTED_MODULE_0__.ImageProcessor { }
 
 
+/***/ }),
+
+/***/ "./src/models/idefics3/image_processing_idefics3.js":
+/*!**********************************************************!*\
+  !*** ./src/models/idefics3/image_processing_idefics3.js ***!
+  \**********************************************************/
+/***/ ((__unused_webpack___webpack_module__, __webpack_exports__, __webpack_require__) => {
+
+__webpack_require__.r(__webpack_exports__);
+/* harmony export */ __webpack_require__.d(__webpack_exports__, {
+/* harmony export */   Idefics3ImageProcessor: () => (/* binding */ Idefics3ImageProcessor)
+/* harmony export */ });
+/* harmony import */ var _base_image_processors_utils_js__WEBPACK_IMPORTED_MODULE_0__ = __webpack_require__(/*! ../../base/image_processors_utils.js */ "./src/base/image_processors_utils.js");
+/* harmony import */ var _utils_tensor_js__WEBPACK_IMPORTED_MODULE_1__ = __webpack_require__(/*! ../../utils/tensor.js */ "./src/utils/tensor.js");
+
+
+
+
+
+class Idefics3ImageProcessor extends _base_image_processors_utils_js__WEBPACK_IMPORTED_MODULE_0__.ImageProcessor {
+    constructor(config) {
+        super(config);
+
+        this.do_image_splitting = config.do_image_splitting ?? true;
+        this.max_image_size = config.max_image_size;
+    }
+
+    /**
+     * @typedef {import('../../utils/image.js').RawImage} RawImage
+     * @typedef {import('../../utils/tensor.js').Tensor} Tensor
+     */
+
+    /**
+     * Calculate size to resize images to, to be multiples of `vision_encoder_max_size` while preserving the aspect ratio.
+     * @param {Tensor} pixel_values Tensor of the image to resize.
+     * @param {number} vision_encoder_max_size Maximum size of the output image. If the image is larger than this size,
+     * it will be split into patches of this size, and the original image will be concatenated with the patches, resized to max_size.
+     */
+    get_resize_for_vision_encoder(pixel_values, vision_encoder_max_size) {
+        let [height, width] = pixel_values.dims.slice(-2);
+
+        const aspect_ratio = width / height;
+        if (width >= height) {
+            width = Math.ceil(width / vision_encoder_max_size) * vision_encoder_max_size;
+            height = Math.floor(width / aspect_ratio);
+            height = Math.ceil(height / vision_encoder_max_size) * vision_encoder_max_size;
+        } else {
+            height = Math.ceil(height / vision_encoder_max_size) * vision_encoder_max_size;
+            width = Math.floor(height * aspect_ratio);
+            width = Math.ceil(width / vision_encoder_max_size) * vision_encoder_max_size;
+        }
+        return { height, width };
+    }
+
+    /** @param {RawImage|RawImage[]|RawImage[][]} images */
+    async _call(images, {
+        do_image_splitting = null,
+        return_row_col_info = false,
+    } = {}) {
+
+        /** @type {RawImage[][]} */
+        let batched_2d_images;
+        if (!Array.isArray(images)) {
+            batched_2d_images = [[images]];
+        } else {
+            if (images.length === 0 || !images[0]) {
+                throw new Error("No images provided.");
+            }
+            if (!Array.isArray(images[0])) {
+                batched_2d_images = [/** @type {RawImage[]} */(images)];
+            } else {
+                batched_2d_images = /** @type {RawImage[][]} */(images);
+            }
+        }
+
+        // List of tensors, each with shape [patches, channels, height, width]
+        let all_pixel_values = [];
+        let images_list_rows = [];
+        let images_list_cols = [];
+
+        const original_sizes = [];
+        const reshaped_input_sizes = [];
+        for (const image_batch of batched_2d_images) {
+
+            let images_list = await Promise.all(image_batch.map(x => this.preprocess(x)));
+
+            // Original sizes of images
+            original_sizes.push(...images_list.map(x => x.original_size));
+
+            // Reshaped sizes of images, before padding or cropping
+            reshaped_input_sizes.push(...images_list.map(x => x.reshaped_input_size));
+
+            // Convert images to 4D tensors for easier processing
+            images_list.forEach(x => x.pixel_values.unsqueeze_(0));
+
+            const { longest_edge } = this.max_image_size;
+
+            /** @type {Tensor[]} */
+            let images_tensor;
+            if (do_image_splitting ?? this.do_image_splitting) {
+                let image_rows = new Array(images_list.length);
+                let image_cols = new Array(images_list.length);
+
+                // We first resize both height and width of each image to the nearest max_image_size multiple, disregarding the aspect ratio
+                images_tensor = await Promise.all(images_list.map(async (x, i) => {
+                    const new_size = this.get_resize_for_vision_encoder(x.pixel_values, longest_edge);
+
+                    const resized = await (0,_utils_tensor_js__WEBPACK_IMPORTED_MODULE_1__.interpolate_4d)(x.pixel_values, {
+                        size: [new_size.height, new_size.width],
+                    });
+
+                    const { frames, num_splits_h, num_splits_w } = await this.split_image(resized, this.max_image_size);
+                    image_rows[i] = num_splits_h;
+                    image_cols[i] = num_splits_w;
+                    return (0,_utils_tensor_js__WEBPACK_IMPORTED_MODULE_1__.cat)(frames, 0);
+                }));
+
+                images_list_rows.push(image_rows);
+                images_list_cols.push(image_cols);
+
+            } else {
+                /** @type {[number, number]} */
+                const size = [longest_edge, longest_edge];
+                images_tensor = await Promise.all(
+                    images_list.map(x => (0,_utils_tensor_js__WEBPACK_IMPORTED_MODULE_1__.interpolate_4d)(x.pixel_values, { size }))
+                );
+
+                images_list_rows.push(new Array(images_list.length).fill(0));
+                images_list_cols.push(new Array(images_list.length).fill(0));
+            }
+
+            all_pixel_values.push((0,_utils_tensor_js__WEBPACK_IMPORTED_MODULE_1__.cat)(images_tensor, 0));
+        }
+
+        const batch_size = all_pixel_values.length;
+        const [n, c, h, w] = all_pixel_values[0].dims;
+
+        // Stack pixel values
+        let pixel_values;
+        let pixel_attention_mask;
+        if (batch_size === 1) {
+            pixel_values = all_pixel_values[0].unsqueeze_(0);
+            pixel_attention_mask = (0,_utils_tensor_js__WEBPACK_IMPORTED_MODULE_1__.full)([batch_size, n, h, w], true);
+        } else {
+            // Add padding (if necessary) to images with less patches than the maximum number of patches
+            const max_num_patches = Math.max(...all_pixel_values.map(x => x.dims.at(0)));
+
+            pixel_attention_mask = (0,_utils_tensor_js__WEBPACK_IMPORTED_MODULE_1__.full)([batch_size, max_num_patches, h, w], true);
+            const pixel_attention_mask_data = pixel_attention_mask.data;
+            const pixel_attention_mask_stride = max_num_patches * h * w;
+            for (let i = 0; i < batch_size; ++i) {
+                const num_patches = all_pixel_values[i].dims[0];
+                if (num_patches < max_num_patches) {
+                    all_pixel_values[i] = (0,_utils_tensor_js__WEBPACK_IMPORTED_MODULE_1__.cat)([
+                        all_pixel_values[i],
+                        (0,_utils_tensor_js__WEBPACK_IMPORTED_MODULE_1__.full)([max_num_patches - num_patches, c, h, w], 0),
+                    ], 0);
+
+                    const start_offset = i * pixel_attention_mask_stride + num_patches * h * w;
+                    const end_offset = (i + 1) * pixel_attention_mask_stride;
+                    pixel_attention_mask_data.fill(false, start_offset, end_offset);
+                }
+            }
+            pixel_values = (0,_utils_tensor_js__WEBPACK_IMPORTED_MODULE_1__.stack)(all_pixel_values, 0);
+        }
+
+        return {
+            pixel_values,
+            pixel_attention_mask,
+
+            original_sizes,
+            reshaped_input_sizes,
+            ...(
+                return_row_col_info
+                    ? { rows: images_list_rows, cols: images_list_cols }
+                    : {}
+            ),
+        }
+    }
+
+    async split_image(pixel_values, { longest_edge }) {
+        const max_height = longest_edge;
+        const max_width = longest_edge;
+
+        const frames = [];
+
+        const [height, width] = pixel_values.dims.slice(-2);
+
+        let num_splits_h = 0, num_splits_w = 0;
+
+        if (height > max_height || width > max_width) {
+            // Calculate the number of splits
+            num_splits_h = Math.ceil(height / max_height);
+            num_splits_w = Math.ceil(width / max_width);
+
+            // Calculate the optimal width and height for the sub-images
+            const optimal_height = Math.ceil(height / num_splits_h);
+            const optimal_width = Math.ceil(width / num_splits_w);
+
+            // Iterate through each row and column
+            for (let r = 0; r < num_splits_h; r++) {
+                for (let c = 0; c < num_splits_w; c++) {
+                    // Calculate the starting point of the crop
+                    const start_x = c * optimal_width;
+                    const start_y = r * optimal_height;
+
+                    // Calculate the ending point of the crop
+                    const end_x = Math.min(start_x + optimal_width, width);
+                    const end_y = Math.min(start_y + optimal_height, height);
+
+                    // Crop the image
+                    frames.push(pixel_values.slice(null, null, [start_y, end_y], [start_x, end_x]));
+                }
+            }
+
+            // Resize the global image to match max dimensions for memory efficiency
+            const global_image_height = max_height;
+            const global_image_width = max_width;
+
+            if (height !== global_image_height || width !== global_image_width) {
+                pixel_values = await (0,_utils_tensor_js__WEBPACK_IMPORTED_MODULE_1__.interpolate_4d)(pixel_values, {
+                    size: [global_image_height, global_image_width],
+                })
+            }
+        }
+
+        frames.push(pixel_values);
+
+        return { frames, num_splits_h, num_splits_w };
+    }
+}
+
+
+/***/ }),
+
+/***/ "./src/models/idefics3/processing_idefics3.js":
+/*!****************************************************!*\
+  !*** ./src/models/idefics3/processing_idefics3.js ***!
+  \****************************************************/
+/***/ ((__unused_webpack___webpack_module__, __webpack_exports__, __webpack_require__) => {
+
+__webpack_require__.r(__webpack_exports__);
+/* harmony export */ __webpack_require__.d(__webpack_exports__, {
+/* harmony export */   Idefics3Processor: () => (/* binding */ Idefics3Processor)
+/* harmony export */ });
+/* harmony import */ var _base_processing_utils_js__WEBPACK_IMPORTED_MODULE_0__ = __webpack_require__(/*! ../../base/processing_utils.js */ "./src/base/processing_utils.js");
+/* harmony import */ var _auto_image_processing_auto_js__WEBPACK_IMPORTED_MODULE_1__ = __webpack_require__(/*! ../auto/image_processing_auto.js */ "./src/models/auto/image_processing_auto.js");
+/* harmony import */ var _tokenizers_js__WEBPACK_IMPORTED_MODULE_2__ = __webpack_require__(/*! ../../tokenizers.js */ "./src/tokenizers.js");
+/* harmony import */ var _utils_image_js__WEBPACK_IMPORTED_MODULE_3__ = __webpack_require__(/*! ../../utils/image.js */ "./src/utils/image.js");
+/* harmony import */ var _utils_core_js__WEBPACK_IMPORTED_MODULE_4__ = __webpack_require__(/*! ../../utils/core.js */ "./src/utils/core.js");
+
+
+
+
+
+
+
+/**
+ * Prompt with expanded image tokens for when the image is split into patches.
+ * @private
+ */
+function _prompt_split_image(image_seq_len, image_rows, image_cols, fake_token_around_image, image_token, global_img_token) {
+    let text_split_images = "";
+    for (let n_h = 0; n_h < image_rows; ++n_h) {
+        for (let n_w = 0; n_w < image_cols; ++n_w) {
+            text_split_images += (
+                fake_token_around_image +
+                `<row_${n_h + 1}_col_${n_w + 1}>` +
+                image_token.repeat(image_seq_len)
+            );
+        }
+        text_split_images += "\n";
+    }
+
+    text_split_images += (
+        `\n${fake_token_around_image}` +
+        `${global_img_token}` +
+        image_token.repeat(image_seq_len) +
+        `${fake_token_around_image}`
+    );
+    return text_split_images;
+}
+
+/**
+ * Prompt with expanded image tokens for a single image.
+ * @private
+ */
+function _prompt_single_image(image_seq_len, fake_token_around_image, image_token, global_img_token) {
+    return (
+        `${fake_token_around_image}` +
+        `${global_img_token}` +
+        image_token.repeat(image_seq_len) +
+        `${fake_token_around_image}`
+    );
+}
+
+function get_image_prompt_string(image_rows, image_cols, image_seq_len, fake_token_around_image, image_token, global_img_token) {
+    if (image_rows === 0 && image_cols === 0) {
+        return _prompt_single_image(
+            image_seq_len,
+            fake_token_around_image,
+            image_token,
+            global_img_token
+        );
+    }
+    return _prompt_split_image(
+        image_seq_len, image_rows, image_cols, fake_token_around_image, image_token, global_img_token
+    );
+}
+
+
+class Idefics3Processor extends _base_processing_utils_js__WEBPACK_IMPORTED_MODULE_0__.Processor {
+    static image_processor_class = _auto_image_processing_auto_js__WEBPACK_IMPORTED_MODULE_1__.AutoImageProcessor
+    static tokenizer_class = _tokenizers_js__WEBPACK_IMPORTED_MODULE_2__.AutoTokenizer
+    static uses_processor_config = true;
+
+    fake_image_token = "<fake_token_around_image>";
+    image_token = "<image>";
+    global_img_token = "<global-img>";
+
+    /**
+     * 
+     * @param {string|string[]} text 
+     * @param {RawImage|RawImage[]|RawImage[][]} images  
+     * @returns {Promise<any>}
+     */
+    async _call(text, images = null, options = {}) {
+        options.return_row_col_info ??= true;
+
+        let image_inputs;
+
+        if (images) {
+            image_inputs = await this.image_processor(images, options);
+        }
+
+        // NOTE: We assume text is present
+        if (!Array.isArray(text)) {
+            text = [text];
+        }
+
+        const image_rows = image_inputs.rows ?? [new Array(text.length).fill(0)];
+        const image_cols = image_inputs.cols ?? [new Array(text.length).fill(0)];
+
+        const image_seq_len = this.config.image_seq_len;
+        const n_images_in_text = []
+        const prompt_strings = [];
+        for (let i = 0; i < text.length; ++i) {
+            const sample = text[i];
+            const sample_rows = image_rows[i];
+            const sample_cols = image_cols[i];
+
+            n_images_in_text.push((0,_utils_core_js__WEBPACK_IMPORTED_MODULE_4__.count)(sample, this.image_token));
+
+            // Replace the image token with fake tokens around the expanded image token sequence of length `image_seq_len`
+            const image_prompt_strings = sample_rows.map(
+                (n_rows, j) => get_image_prompt_string(
+                    n_rows,
+                    sample_cols[j],
+                    image_seq_len,
+                    this.fake_image_token,
+                    this.image_token,
+                    this.global_img_token,
+                )
+            );
+
+            const split_sample = sample.split(this.image_token);
+            if (split_sample.length === 0) {
+                throw new Error("The image token should be present in the text.");
+            }
+
+            // Place in the image prompt strings where the image tokens are
+            let new_sample = split_sample[0];
+            for (let j = 0; j < image_prompt_strings.length; ++j) {
+                new_sample += image_prompt_strings[j] + split_sample[j + 1];
+            }
+            prompt_strings.push(new_sample);
+        }
+
+        const text_inputs = this.tokenizer(prompt_strings);
+
+        return {
+            ...text_inputs,
+            ...image_inputs,
+        }
+    }
+}
+
+
 /***/ }),
 
 /***/ "./src/models/image_processors.js":
@@ -16797,40 +17340,41 @@ __webpack_require__.r(__webpack_exports__);
 /* harmony export */   DonutImageProcessor: () => (/* reexport safe */ _donut_image_processing_donut_js__WEBPACK_IMPORTED_MODULE_7__.DonutImageProcessor),
 /* harmony export */   EfficientNetImageProcessor: () => (/* reexport safe */ _efficientnet_image_processing_efficientnet_js__WEBPACK_IMPORTED_MODULE_9__.EfficientNetImageProcessor),
 /* harmony export */   GLPNFeatureExtractor: () => (/* reexport safe */ _glpn_image_processing_glpn_js__WEBPACK_IMPORTED_MODULE_10__.GLPNFeatureExtractor),
-/* harmony export */   JinaCLIPImageProcessor: () => (/* reexport safe */ _jina_clip_image_processing_jina_clip_js__WEBPACK_IMPORTED_MODULE_12__.JinaCLIPImageProcessor),
-/* harmony export */   LlavaOnevisionImageProcessor: () => (/* reexport safe */ _llava_onevision_image_processing_llava_onevision_js__WEBPACK_IMPORTED_MODULE_13__.LlavaOnevisionImageProcessor),
-/* harmony export */   Mask2FormerImageProcessor: () => (/* reexport safe */ _mask2former_image_processing_mask2former_js__WEBPACK_IMPORTED_MODULE_14__.Mask2FormerImageProcessor),
-/* harmony export */   MaskFormerFeatureExtractor: () => (/* reexport safe */ _maskformer_image_processing_maskformer_js__WEBPACK_IMPORTED_MODULE_15__.MaskFormerFeatureExtractor),
-/* harmony export */   MaskFormerImageProcessor: () => (/* reexport safe */ _maskformer_image_processing_maskformer_js__WEBPACK_IMPORTED_MODULE_15__.MaskFormerImageProcessor),
-/* harmony export */   MobileNetV1FeatureExtractor: () => (/* reexport safe */ _mobilenet_v1_image_processing_mobilenet_v1_js__WEBPACK_IMPORTED_MODULE_16__.MobileNetV1FeatureExtractor),
-/* harmony export */   MobileNetV1ImageProcessor: () => (/* reexport safe */ _mobilenet_v1_image_processing_mobilenet_v1_js__WEBPACK_IMPORTED_MODULE_16__.MobileNetV1ImageProcessor),
-/* harmony export */   MobileNetV2FeatureExtractor: () => (/* reexport safe */ _mobilenet_v2_image_processing_mobilenet_v2_js__WEBPACK_IMPORTED_MODULE_17__.MobileNetV2FeatureExtractor),
-/* harmony export */   MobileNetV2ImageProcessor: () => (/* reexport safe */ _mobilenet_v2_image_processing_mobilenet_v2_js__WEBPACK_IMPORTED_MODULE_17__.MobileNetV2ImageProcessor),
-/* harmony export */   MobileNetV3FeatureExtractor: () => (/* reexport safe */ _mobilenet_v3_image_processing_mobilenet_v3_js__WEBPACK_IMPORTED_MODULE_18__.MobileNetV3FeatureExtractor),
-/* harmony export */   MobileNetV3ImageProcessor: () => (/* reexport safe */ _mobilenet_v3_image_processing_mobilenet_v3_js__WEBPACK_IMPORTED_MODULE_18__.MobileNetV3ImageProcessor),
-/* harmony export */   MobileNetV4FeatureExtractor: () => (/* reexport safe */ _mobilenet_v4_image_processing_mobilenet_v4_js__WEBPACK_IMPORTED_MODULE_19__.MobileNetV4FeatureExtractor),
-/* harmony export */   MobileNetV4ImageProcessor: () => (/* reexport safe */ _mobilenet_v4_image_processing_mobilenet_v4_js__WEBPACK_IMPORTED_MODULE_19__.MobileNetV4ImageProcessor),
-/* harmony export */   MobileViTFeatureExtractor: () => (/* reexport safe */ _mobilevit_image_processing_mobilevit_js__WEBPACK_IMPORTED_MODULE_20__.MobileViTFeatureExtractor),
-/* harmony export */   MobileViTImageProcessor: () => (/* reexport safe */ _mobilevit_image_processing_mobilevit_js__WEBPACK_IMPORTED_MODULE_20__.MobileViTImageProcessor),
-/* harmony export */   NougatImageProcessor: () => (/* reexport safe */ _nougat_image_processing_nougat_js__WEBPACK_IMPORTED_MODULE_21__.NougatImageProcessor),
-/* harmony export */   OwlViTFeatureExtractor: () => (/* reexport safe */ _owlvit_image_processing_owlvit_js__WEBPACK_IMPORTED_MODULE_23__.OwlViTFeatureExtractor),
-/* harmony export */   OwlViTImageProcessor: () => (/* reexport safe */ _owlvit_image_processing_owlvit_js__WEBPACK_IMPORTED_MODULE_23__.OwlViTImageProcessor),
-/* harmony export */   Owlv2ImageProcessor: () => (/* reexport safe */ _owlv2_image_processing_owlv2_js__WEBPACK_IMPORTED_MODULE_22__.Owlv2ImageProcessor),
-/* harmony export */   PvtImageProcessor: () => (/* reexport safe */ _pvt_image_processing_pvt_js__WEBPACK_IMPORTED_MODULE_24__.PvtImageProcessor),
-/* harmony export */   Qwen2VLImageProcessor: () => (/* reexport safe */ _qwen2_vl_image_processing_qwen2_vl_js__WEBPACK_IMPORTED_MODULE_25__.Qwen2VLImageProcessor),
-/* harmony export */   RTDetrImageProcessor: () => (/* reexport safe */ _rt_detr_image_processing_rt_detr_js__WEBPACK_IMPORTED_MODULE_26__.RTDetrImageProcessor),
-/* harmony export */   SamImageProcessor: () => (/* reexport safe */ _sam_image_processing_sam_js__WEBPACK_IMPORTED_MODULE_27__.SamImageProcessor),
-/* harmony export */   SegformerFeatureExtractor: () => (/* reexport safe */ _segformer_image_processing_segformer_js__WEBPACK_IMPORTED_MODULE_28__.SegformerFeatureExtractor),
-/* harmony export */   SegformerImageProcessor: () => (/* reexport safe */ _segformer_image_processing_segformer_js__WEBPACK_IMPORTED_MODULE_28__.SegformerImageProcessor),
-/* harmony export */   SiglipImageProcessor: () => (/* reexport safe */ _siglip_image_processing_siglip_js__WEBPACK_IMPORTED_MODULE_29__.SiglipImageProcessor),
-/* harmony export */   Swin2SRImageProcessor: () => (/* reexport safe */ _swin2sr_image_processing_swin2sr_js__WEBPACK_IMPORTED_MODULE_30__.Swin2SRImageProcessor),
-/* harmony export */   VLMImageProcessor: () => (/* reexport safe */ _janus_image_processing_janus_js__WEBPACK_IMPORTED_MODULE_11__.VLMImageProcessor),
-/* harmony export */   ViTFeatureExtractor: () => (/* reexport safe */ _vit_image_processing_vit_js__WEBPACK_IMPORTED_MODULE_31__.ViTFeatureExtractor),
-/* harmony export */   ViTImageProcessor: () => (/* reexport safe */ _vit_image_processing_vit_js__WEBPACK_IMPORTED_MODULE_31__.ViTImageProcessor),
-/* harmony export */   VitMatteImageProcessor: () => (/* reexport safe */ _vitmatte_image_processing_vitmatte_js__WEBPACK_IMPORTED_MODULE_32__.VitMatteImageProcessor),
-/* harmony export */   VitPoseImageProcessor: () => (/* reexport safe */ _vitpose_image_processing_vitpose_js__WEBPACK_IMPORTED_MODULE_33__.VitPoseImageProcessor),
-/* harmony export */   YolosFeatureExtractor: () => (/* reexport safe */ _yolos_image_processing_yolos_js__WEBPACK_IMPORTED_MODULE_34__.YolosFeatureExtractor),
-/* harmony export */   YolosImageProcessor: () => (/* reexport safe */ _yolos_image_processing_yolos_js__WEBPACK_IMPORTED_MODULE_34__.YolosImageProcessor)
+/* harmony export */   Idefics3ImageProcessor: () => (/* reexport safe */ _idefics3_image_processing_idefics3_js__WEBPACK_IMPORTED_MODULE_11__.Idefics3ImageProcessor),
+/* harmony export */   JinaCLIPImageProcessor: () => (/* reexport safe */ _jina_clip_image_processing_jina_clip_js__WEBPACK_IMPORTED_MODULE_13__.JinaCLIPImageProcessor),
+/* harmony export */   LlavaOnevisionImageProcessor: () => (/* reexport safe */ _llava_onevision_image_processing_llava_onevision_js__WEBPACK_IMPORTED_MODULE_14__.LlavaOnevisionImageProcessor),
+/* harmony export */   Mask2FormerImageProcessor: () => (/* reexport safe */ _mask2former_image_processing_mask2former_js__WEBPACK_IMPORTED_MODULE_15__.Mask2FormerImageProcessor),
+/* harmony export */   MaskFormerFeatureExtractor: () => (/* reexport safe */ _maskformer_image_processing_maskformer_js__WEBPACK_IMPORTED_MODULE_16__.MaskFormerFeatureExtractor),
+/* harmony export */   MaskFormerImageProcessor: () => (/* reexport safe */ _maskformer_image_processing_maskformer_js__WEBPACK_IMPORTED_MODULE_16__.MaskFormerImageProcessor),
+/* harmony export */   MobileNetV1FeatureExtractor: () => (/* reexport safe */ _mobilenet_v1_image_processing_mobilenet_v1_js__WEBPACK_IMPORTED_MODULE_17__.MobileNetV1FeatureExtractor),
+/* harmony export */   MobileNetV1ImageProcessor: () => (/* reexport safe */ _mobilenet_v1_image_processing_mobilenet_v1_js__WEBPACK_IMPORTED_MODULE_17__.MobileNetV1ImageProcessor),
+/* harmony export */   MobileNetV2FeatureExtractor: () => (/* reexport safe */ _mobilenet_v2_image_processing_mobilenet_v2_js__WEBPACK_IMPORTED_MODULE_18__.MobileNetV2FeatureExtractor),
+/* harmony export */   MobileNetV2ImageProcessor: () => (/* reexport safe */ _mobilenet_v2_image_processing_mobilenet_v2_js__WEBPACK_IMPORTED_MODULE_18__.MobileNetV2ImageProcessor),
+/* harmony export */   MobileNetV3FeatureExtractor: () => (/* reexport safe */ _mobilenet_v3_image_processing_mobilenet_v3_js__WEBPACK_IMPORTED_MODULE_19__.MobileNetV3FeatureExtractor),
+/* harmony export */   MobileNetV3ImageProcessor: () => (/* reexport safe */ _mobilenet_v3_image_processing_mobilenet_v3_js__WEBPACK_IMPORTED_MODULE_19__.MobileNetV3ImageProcessor),
+/* harmony export */   MobileNetV4FeatureExtractor: () => (/* reexport safe */ _mobilenet_v4_image_processing_mobilenet_v4_js__WEBPACK_IMPORTED_MODULE_20__.MobileNetV4FeatureExtractor),
+/* harmony export */   MobileNetV4ImageProcessor: () => (/* reexport safe */ _mobilenet_v4_image_processing_mobilenet_v4_js__WEBPACK_IMPORTED_MODULE_20__.MobileNetV4ImageProcessor),
+/* harmony export */   MobileViTFeatureExtractor: () => (/* reexport safe */ _mobilevit_image_processing_mobilevit_js__WEBPACK_IMPORTED_MODULE_21__.MobileViTFeatureExtractor),
+/* harmony export */   MobileViTImageProcessor: () => (/* reexport safe */ _mobilevit_image_processing_mobilevit_js__WEBPACK_IMPORTED_MODULE_21__.MobileViTImageProcessor),
+/* harmony export */   NougatImageProcessor: () => (/* reexport safe */ _nougat_image_processing_nougat_js__WEBPACK_IMPORTED_MODULE_22__.NougatImageProcessor),
+/* harmony export */   OwlViTFeatureExtractor: () => (/* reexport safe */ _owlvit_image_processing_owlvit_js__WEBPACK_IMPORTED_MODULE_24__.OwlViTFeatureExtractor),
+/* harmony export */   OwlViTImageProcessor: () => (/* reexport safe */ _owlvit_image_processing_owlvit_js__WEBPACK_IMPORTED_MODULE_24__.OwlViTImageProcessor),
+/* harmony export */   Owlv2ImageProcessor: () => (/* reexport safe */ _owlv2_image_processing_owlv2_js__WEBPACK_IMPORTED_MODULE_23__.Owlv2ImageProcessor),
+/* harmony export */   PvtImageProcessor: () => (/* reexport safe */ _pvt_image_processing_pvt_js__WEBPACK_IMPORTED_MODULE_25__.PvtImageProcessor),
+/* harmony export */   Qwen2VLImageProcessor: () => (/* reexport safe */ _qwen2_vl_image_processing_qwen2_vl_js__WEBPACK_IMPORTED_MODULE_26__.Qwen2VLImageProcessor),
+/* harmony export */   RTDetrImageProcessor: () => (/* reexport safe */ _rt_detr_image_processing_rt_detr_js__WEBPACK_IMPORTED_MODULE_27__.RTDetrImageProcessor),
+/* harmony export */   SamImageProcessor: () => (/* reexport safe */ _sam_image_processing_sam_js__WEBPACK_IMPORTED_MODULE_28__.SamImageProcessor),
+/* harmony export */   SegformerFeatureExtractor: () => (/* reexport safe */ _segformer_image_processing_segformer_js__WEBPACK_IMPORTED_MODULE_29__.SegformerFeatureExtractor),
+/* harmony export */   SegformerImageProcessor: () => (/* reexport safe */ _segformer_image_processing_segformer_js__WEBPACK_IMPORTED_MODULE_29__.SegformerImageProcessor),
+/* harmony export */   SiglipImageProcessor: () => (/* reexport safe */ _siglip_image_processing_siglip_js__WEBPACK_IMPORTED_MODULE_30__.SiglipImageProcessor),
+/* harmony export */   Swin2SRImageProcessor: () => (/* reexport safe */ _swin2sr_image_processing_swin2sr_js__WEBPACK_IMPORTED_MODULE_31__.Swin2SRImageProcessor),
+/* harmony export */   VLMImageProcessor: () => (/* reexport safe */ _janus_image_processing_janus_js__WEBPACK_IMPORTED_MODULE_12__.VLMImageProcessor),
+/* harmony export */   ViTFeatureExtractor: () => (/* reexport safe */ _vit_image_processing_vit_js__WEBPACK_IMPORTED_MODULE_32__.ViTFeatureExtractor),
+/* harmony export */   ViTImageProcessor: () => (/* reexport safe */ _vit_image_processing_vit_js__WEBPACK_IMPORTED_MODULE_32__.ViTImageProcessor),
+/* harmony export */   VitMatteImageProcessor: () => (/* reexport safe */ _vitmatte_image_processing_vitmatte_js__WEBPACK_IMPORTED_MODULE_33__.VitMatteImageProcessor),
+/* harmony export */   VitPoseImageProcessor: () => (/* reexport safe */ _vitpose_image_processing_vitpose_js__WEBPACK_IMPORTED_MODULE_34__.VitPoseImageProcessor),
+/* harmony export */   YolosFeatureExtractor: () => (/* reexport safe */ _yolos_image_processing_yolos_js__WEBPACK_IMPORTED_MODULE_35__.YolosFeatureExtractor),
+/* harmony export */   YolosImageProcessor: () => (/* reexport safe */ _yolos_image_processing_yolos_js__WEBPACK_IMPORTED_MODULE_35__.YolosImageProcessor)
 /* harmony export */ });
 /* harmony import */ var _beit_image_processing_beit_js__WEBPACK_IMPORTED_MODULE_0__ = __webpack_require__(/*! ./beit/image_processing_beit.js */ "./src/models/beit/image_processing_beit.js");
 /* harmony import */ var _bit_image_processing_bit_js__WEBPACK_IMPORTED_MODULE_1__ = __webpack_require__(/*! ./bit/image_processing_bit.js */ "./src/models/bit/image_processing_bit.js");
@@ -16843,30 +17387,32 @@ __webpack_require__.r(__webpack_exports__);
 /* harmony import */ var _dpt_image_processing_dpt_js__WEBPACK_IMPORTED_MODULE_8__ = __webpack_require__(/*! ./dpt/image_processing_dpt.js */ "./src/models/dpt/image_processing_dpt.js");
 /* harmony import */ var _efficientnet_image_processing_efficientnet_js__WEBPACK_IMPORTED_MODULE_9__ = __webpack_require__(/*! ./efficientnet/image_processing_efficientnet.js */ "./src/models/efficientnet/image_processing_efficientnet.js");
 /* harmony import */ var _glpn_image_processing_glpn_js__WEBPACK_IMPORTED_MODULE_10__ = __webpack_require__(/*! ./glpn/image_processing_glpn.js */ "./src/models/glpn/image_processing_glpn.js");
-/* harmony import */ var _janus_image_processing_janus_js__WEBPACK_IMPORTED_MODULE_11__ = __webpack_require__(/*! ./janus/image_processing_janus.js */ "./src/models/janus/image_processing_janus.js");
-/* harmony import */ var _jina_clip_image_processing_jina_clip_js__WEBPACK_IMPORTED_MODULE_12__ = __webpack_require__(/*! ./jina_clip/image_processing_jina_clip.js */ "./src/models/jina_clip/image_processing_jina_clip.js");
-/* harmony import */ var _llava_onevision_image_processing_llava_onevision_js__WEBPACK_IMPORTED_MODULE_13__ = __webpack_require__(/*! ./llava_onevision/image_processing_llava_onevision.js */ "./src/models/llava_onevision/image_processing_llava_onevision.js");
-/* harmony import */ var _mask2former_image_processing_mask2former_js__WEBPACK_IMPORTED_MODULE_14__ = __webpack_require__(/*! ./mask2former/image_processing_mask2former.js */ "./src/models/mask2former/image_processing_mask2former.js");
-/* harmony import */ var _maskformer_image_processing_maskformer_js__WEBPACK_IMPORTED_MODULE_15__ = __webpack_require__(/*! ./maskformer/image_processing_maskformer.js */ "./src/models/maskformer/image_processing_maskformer.js");
-/* harmony import */ var _mobilenet_v1_image_processing_mobilenet_v1_js__WEBPACK_IMPORTED_MODULE_16__ = __webpack_require__(/*! ./mobilenet_v1/image_processing_mobilenet_v1.js */ "./src/models/mobilenet_v1/image_processing_mobilenet_v1.js");
-/* harmony import */ var _mobilenet_v2_image_processing_mobilenet_v2_js__WEBPACK_IMPORTED_MODULE_17__ = __webpack_require__(/*! ./mobilenet_v2/image_processing_mobilenet_v2.js */ "./src/models/mobilenet_v2/image_processing_mobilenet_v2.js");
-/* harmony import */ var _mobilenet_v3_image_processing_mobilenet_v3_js__WEBPACK_IMPORTED_MODULE_18__ = __webpack_require__(/*! ./mobilenet_v3/image_processing_mobilenet_v3.js */ "./src/models/mobilenet_v3/image_processing_mobilenet_v3.js");
-/* harmony import */ var _mobilenet_v4_image_processing_mobilenet_v4_js__WEBPACK_IMPORTED_MODULE_19__ = __webpack_require__(/*! ./mobilenet_v4/image_processing_mobilenet_v4.js */ "./src/models/mobilenet_v4/image_processing_mobilenet_v4.js");
-/* harmony import */ var _mobilevit_image_processing_mobilevit_js__WEBPACK_IMPORTED_MODULE_20__ = __webpack_require__(/*! ./mobilevit/image_processing_mobilevit.js */ "./src/models/mobilevit/image_processing_mobilevit.js");
-/* harmony import */ var _nougat_image_processing_nougat_js__WEBPACK_IMPORTED_MODULE_21__ = __webpack_require__(/*! ./nougat/image_processing_nougat.js */ "./src/models/nougat/image_processing_nougat.js");
-/* harmony import */ var _owlv2_image_processing_owlv2_js__WEBPACK_IMPORTED_MODULE_22__ = __webpack_require__(/*! ./owlv2/image_processing_owlv2.js */ "./src/models/owlv2/image_processing_owlv2.js");
-/* harmony import */ var _owlvit_image_processing_owlvit_js__WEBPACK_IMPORTED_MODULE_23__ = __webpack_require__(/*! ./owlvit/image_processing_owlvit.js */ "./src/models/owlvit/image_processing_owlvit.js");
-/* harmony import */ var _pvt_image_processing_pvt_js__WEBPACK_IMPORTED_MODULE_24__ = __webpack_require__(/*! ./pvt/image_processing_pvt.js */ "./src/models/pvt/image_processing_pvt.js");
-/* harmony import */ var _qwen2_vl_image_processing_qwen2_vl_js__WEBPACK_IMPORTED_MODULE_25__ = __webpack_require__(/*! ./qwen2_vl/image_processing_qwen2_vl.js */ "./src/models/qwen2_vl/image_processing_qwen2_vl.js");
-/* harmony import */ var _rt_detr_image_processing_rt_detr_js__WEBPACK_IMPORTED_MODULE_26__ = __webpack_require__(/*! ./rt_detr/image_processing_rt_detr.js */ "./src/models/rt_detr/image_processing_rt_detr.js");
-/* harmony import */ var _sam_image_processing_sam_js__WEBPACK_IMPORTED_MODULE_27__ = __webpack_require__(/*! ./sam/image_processing_sam.js */ "./src/models/sam/image_processing_sam.js");
-/* harmony import */ var _segformer_image_processing_segformer_js__WEBPACK_IMPORTED_MODULE_28__ = __webpack_require__(/*! ./segformer/image_processing_segformer.js */ "./src/models/segformer/image_processing_segformer.js");
-/* harmony import */ var _siglip_image_processing_siglip_js__WEBPACK_IMPORTED_MODULE_29__ = __webpack_require__(/*! ./siglip/image_processing_siglip.js */ "./src/models/siglip/image_processing_siglip.js");
-/* harmony import */ var _swin2sr_image_processing_swin2sr_js__WEBPACK_IMPORTED_MODULE_30__ = __webpack_require__(/*! ./swin2sr/image_processing_swin2sr.js */ "./src/models/swin2sr/image_processing_swin2sr.js");
-/* harmony import */ var _vit_image_processing_vit_js__WEBPACK_IMPORTED_MODULE_31__ = __webpack_require__(/*! ./vit/image_processing_vit.js */ "./src/models/vit/image_processing_vit.js");
-/* harmony import */ var _vitmatte_image_processing_vitmatte_js__WEBPACK_IMPORTED_MODULE_32__ = __webpack_require__(/*! ./vitmatte/image_processing_vitmatte.js */ "./src/models/vitmatte/image_processing_vitmatte.js");
-/* harmony import */ var _vitpose_image_processing_vitpose_js__WEBPACK_IMPORTED_MODULE_33__ = __webpack_require__(/*! ./vitpose/image_processing_vitpose.js */ "./src/models/vitpose/image_processing_vitpose.js");
-/* harmony import */ var _yolos_image_processing_yolos_js__WEBPACK_IMPORTED_MODULE_34__ = __webpack_require__(/*! ./yolos/image_processing_yolos.js */ "./src/models/yolos/image_processing_yolos.js");
+/* harmony import */ var _idefics3_image_processing_idefics3_js__WEBPACK_IMPORTED_MODULE_11__ = __webpack_require__(/*! ./idefics3/image_processing_idefics3.js */ "./src/models/idefics3/image_processing_idefics3.js");
+/* harmony import */ var _janus_image_processing_janus_js__WEBPACK_IMPORTED_MODULE_12__ = __webpack_require__(/*! ./janus/image_processing_janus.js */ "./src/models/janus/image_processing_janus.js");
+/* harmony import */ var _jina_clip_image_processing_jina_clip_js__WEBPACK_IMPORTED_MODULE_13__ = __webpack_require__(/*! ./jina_clip/image_processing_jina_clip.js */ "./src/models/jina_clip/image_processing_jina_clip.js");
+/* harmony import */ var _llava_onevision_image_processing_llava_onevision_js__WEBPACK_IMPORTED_MODULE_14__ = __webpack_require__(/*! ./llava_onevision/image_processing_llava_onevision.js */ "./src/models/llava_onevision/image_processing_llava_onevision.js");
+/* harmony import */ var _mask2former_image_processing_mask2former_js__WEBPACK_IMPORTED_MODULE_15__ = __webpack_require__(/*! ./mask2former/image_processing_mask2former.js */ "./src/models/mask2former/image_processing_mask2former.js");
+/* harmony import */ var _maskformer_image_processing_maskformer_js__WEBPACK_IMPORTED_MODULE_16__ = __webpack_require__(/*! ./maskformer/image_processing_maskformer.js */ "./src/models/maskformer/image_processing_maskformer.js");
+/* harmony import */ var _mobilenet_v1_image_processing_mobilenet_v1_js__WEBPACK_IMPORTED_MODULE_17__ = __webpack_require__(/*! ./mobilenet_v1/image_processing_mobilenet_v1.js */ "./src/models/mobilenet_v1/image_processing_mobilenet_v1.js");
+/* harmony import */ var _mobilenet_v2_image_processing_mobilenet_v2_js__WEBPACK_IMPORTED_MODULE_18__ = __webpack_require__(/*! ./mobilenet_v2/image_processing_mobilenet_v2.js */ "./src/models/mobilenet_v2/image_processing_mobilenet_v2.js");
+/* harmony import */ var _mobilenet_v3_image_processing_mobilenet_v3_js__WEBPACK_IMPORTED_MODULE_19__ = __webpack_require__(/*! ./mobilenet_v3/image_processing_mobilenet_v3.js */ "./src/models/mobilenet_v3/image_processing_mobilenet_v3.js");
+/* harmony import */ var _mobilenet_v4_image_processing_mobilenet_v4_js__WEBPACK_IMPORTED_MODULE_20__ = __webpack_require__(/*! ./mobilenet_v4/image_processing_mobilenet_v4.js */ "./src/models/mobilenet_v4/image_processing_mobilenet_v4.js");
+/* harmony import */ var _mobilevit_image_processing_mobilevit_js__WEBPACK_IMPORTED_MODULE_21__ = __webpack_require__(/*! ./mobilevit/image_processing_mobilevit.js */ "./src/models/mobilevit/image_processing_mobilevit.js");
+/* harmony import */ var _nougat_image_processing_nougat_js__WEBPACK_IMPORTED_MODULE_22__ = __webpack_require__(/*! ./nougat/image_processing_nougat.js */ "./src/models/nougat/image_processing_nougat.js");
+/* harmony import */ var _owlv2_image_processing_owlv2_js__WEBPACK_IMPORTED_MODULE_23__ = __webpack_require__(/*! ./owlv2/image_processing_owlv2.js */ "./src/models/owlv2/image_processing_owlv2.js");
+/* harmony import */ var _owlvit_image_processing_owlvit_js__WEBPACK_IMPORTED_MODULE_24__ = __webpack_require__(/*! ./owlvit/image_processing_owlvit.js */ "./src/models/owlvit/image_processing_owlvit.js");
+/* harmony import */ var _pvt_image_processing_pvt_js__WEBPACK_IMPORTED_MODULE_25__ = __webpack_require__(/*! ./pvt/image_processing_pvt.js */ "./src/models/pvt/image_processing_pvt.js");
+/* harmony import */ var _qwen2_vl_image_processing_qwen2_vl_js__WEBPACK_IMPORTED_MODULE_26__ = __webpack_require__(/*! ./qwen2_vl/image_processing_qwen2_vl.js */ "./src/models/qwen2_vl/image_processing_qwen2_vl.js");
+/* harmony import */ var _rt_detr_image_processing_rt_detr_js__WEBPACK_IMPORTED_MODULE_27__ = __webpack_require__(/*! ./rt_detr/image_processing_rt_detr.js */ "./src/models/rt_detr/image_processing_rt_detr.js");
+/* harmony import */ var _sam_image_processing_sam_js__WEBPACK_IMPORTED_MODULE_28__ = __webpack_require__(/*! ./sam/image_processing_sam.js */ "./src/models/sam/image_processing_sam.js");
+/* harmony import */ var _segformer_image_processing_segformer_js__WEBPACK_IMPORTED_MODULE_29__ = __webpack_require__(/*! ./segformer/image_processing_segformer.js */ "./src/models/segformer/image_processing_segformer.js");
+/* harmony import */ var _siglip_image_processing_siglip_js__WEBPACK_IMPORTED_MODULE_30__ = __webpack_require__(/*! ./siglip/image_processing_siglip.js */ "./src/models/siglip/image_processing_siglip.js");
+/* harmony import */ var _swin2sr_image_processing_swin2sr_js__WEBPACK_IMPORTED_MODULE_31__ = __webpack_require__(/*! ./swin2sr/image_processing_swin2sr.js */ "./src/models/swin2sr/image_processing_swin2sr.js");
+/* harmony import */ var _vit_image_processing_vit_js__WEBPACK_IMPORTED_MODULE_32__ = __webpack_require__(/*! ./vit/image_processing_vit.js */ "./src/models/vit/image_processing_vit.js");
+/* harmony import */ var _vitmatte_image_processing_vitmatte_js__WEBPACK_IMPORTED_MODULE_33__ = __webpack_require__(/*! ./vitmatte/image_processing_vitmatte.js */ "./src/models/vitmatte/image_processing_vitmatte.js");
+/* harmony import */ var _vitpose_image_processing_vitpose_js__WEBPACK_IMPORTED_MODULE_34__ = __webpack_require__(/*! ./vitpose/image_processing_vitpose.js */ "./src/models/vitpose/image_processing_vitpose.js");
+/* harmony import */ var _yolos_image_processing_yolos_js__WEBPACK_IMPORTED_MODULE_35__ = __webpack_require__(/*! ./yolos/image_processing_yolos.js */ "./src/models/yolos/image_processing_yolos.js");
+
 
 
 
@@ -17616,6 +18162,105 @@ class OwlViTProcessor extends _base_processing_utils_js__WEBPACK_IMPORTED_MODULE
 }
 
 
+/***/ }),
+
+/***/ "./src/models/paligemma/processing_paligemma.js":
+/*!******************************************************!*\
+  !*** ./src/models/paligemma/processing_paligemma.js ***!
+  \******************************************************/
+/***/ ((__unused_webpack___webpack_module__, __webpack_exports__, __webpack_require__) => {
+
+__webpack_require__.r(__webpack_exports__);
+/* harmony export */ __webpack_require__.d(__webpack_exports__, {
+/* harmony export */   PaliGemmaProcessor: () => (/* binding */ PaliGemmaProcessor)
+/* harmony export */ });
+/* harmony import */ var _base_processing_utils_js__WEBPACK_IMPORTED_MODULE_0__ = __webpack_require__(/*! ../../base/processing_utils.js */ "./src/base/processing_utils.js");
+/* harmony import */ var _auto_image_processing_auto_js__WEBPACK_IMPORTED_MODULE_1__ = __webpack_require__(/*! ../auto/image_processing_auto.js */ "./src/models/auto/image_processing_auto.js");
+/* harmony import */ var _tokenizers_js__WEBPACK_IMPORTED_MODULE_2__ = __webpack_require__(/*! ../../tokenizers.js */ "./src/tokenizers.js");
+
+
+
+
+const IMAGE_TOKEN = "<image>";
+
+function build_string_from_input(
+    prompt,
+    bos_token,
+    image_seq_len,
+    image_token,
+    num_images,
+) {
+    return `${image_token.repeat(image_seq_len * num_images)}${bos_token}${prompt}\n`
+}
+
+class PaliGemmaProcessor extends _base_processing_utils_js__WEBPACK_IMPORTED_MODULE_0__.Processor {
+    static tokenizer_class = _tokenizers_js__WEBPACK_IMPORTED_MODULE_2__.AutoTokenizer
+    static image_processor_class = _auto_image_processing_auto_js__WEBPACK_IMPORTED_MODULE_1__.AutoImageProcessor
+    static uses_processor_config = false;
+
+    /**
+     * @typedef {import('../../utils/image.js').RawImage} RawImage
+     */
+
+    // `images` is required, `text` is optional
+    async _call(/** @type {RawImage|RawImage[]} */ images, text = null, kwargs = {}) {
+        if (!text) {
+            console.warn(
+                "You are using PaliGemma without a text prefix. It will perform as a picture-captioning model."
+            )
+            text = ""
+        }
+
+        if (!Array.isArray(images)) {
+            images = [images]
+        }
+
+        if (!Array.isArray(text)) {
+            text = [text]
+        }
+
+        const bos_token = this.tokenizer.bos_token;
+        const image_seq_length = this.image_processor.config.image_seq_length;
+        let input_strings;
+        if (text.some((t) => t.includes(IMAGE_TOKEN))) {
+            input_strings = text.map(
+                sample => {
+                    const expanded_sample = sample.replaceAll(IMAGE_TOKEN, IMAGE_TOKEN.repeat(image_seq_length));
+                    const bos_rfind_index = expanded_sample.lastIndexOf(IMAGE_TOKEN);
+                    const bos_index = bos_rfind_index === -1 ? 0 : bos_rfind_index + IMAGE_TOKEN.length;
+                    return expanded_sample.slice(0, bos_index) + bos_token + expanded_sample.slice(bos_index) + "\n";
+                }
+            )
+        } else {
+            console.warn(
+                "You are passing both `text` and `images` to `PaliGemmaProcessor`. The processor expects special " +
+                "image tokens in the text, as many tokens as there are images per each text. It is recommended to " +
+                "add `<image>` tokens in the very beginning of your text. For this call, we will infer how many images " +
+                "each text has and add special tokens."
+            )
+
+            input_strings = text.map(
+                sample => build_string_from_input(
+                    sample,
+                    bos_token,
+                    image_seq_length,
+                    IMAGE_TOKEN,
+                    images.length,
+                )
+            )
+        }
+
+        const text_inputs = this.tokenizer(input_strings, kwargs);
+        const image_inputs = await this.image_processor(images, kwargs);
+
+        return {
+            ...image_inputs,
+            ...text_inputs,
+        }
+    }
+}
+
+
 /***/ }),
 
 /***/ "./src/models/processors.js":
@@ -17627,28 +18272,34 @@ class OwlViTProcessor extends _base_processing_utils_js__WEBPACK_IMPORTED_MODULE
 __webpack_require__.r(__webpack_exports__);
 /* harmony export */ __webpack_require__.d(__webpack_exports__, {
 /* harmony export */   Florence2Processor: () => (/* reexport safe */ _florence2_processing_florence2_js__WEBPACK_IMPORTED_MODULE_0__.Florence2Processor),
-/* harmony export */   JinaCLIPProcessor: () => (/* reexport safe */ _jina_clip_processing_jina_clip_js__WEBPACK_IMPORTED_MODULE_3__.JinaCLIPProcessor),
+/* harmony export */   Idefics3Processor: () => (/* reexport safe */ _idefics3_processing_idefics3_js__WEBPACK_IMPORTED_MODULE_2__.Idefics3Processor),
+/* harmony export */   JinaCLIPProcessor: () => (/* reexport safe */ _jina_clip_processing_jina_clip_js__WEBPACK_IMPORTED_MODULE_4__.JinaCLIPProcessor),
 /* harmony export */   MgpstrProcessor: () => (/* reexport safe */ _mgp_str_processing_mgp_str_js__WEBPACK_IMPORTED_MODULE_1__.MgpstrProcessor),
-/* harmony export */   OwlViTProcessor: () => (/* reexport safe */ _owlvit_processing_owlvit_js__WEBPACK_IMPORTED_MODULE_4__.OwlViTProcessor),
-/* harmony export */   PyAnnoteProcessor: () => (/* reexport safe */ _pyannote_processing_pyannote_js__WEBPACK_IMPORTED_MODULE_5__.PyAnnoteProcessor),
-/* harmony export */   Qwen2VLProcessor: () => (/* reexport safe */ _qwen2_vl_processing_qwen2_vl_js__WEBPACK_IMPORTED_MODULE_6__.Qwen2VLProcessor),
-/* harmony export */   SamProcessor: () => (/* reexport safe */ _sam_processing_sam_js__WEBPACK_IMPORTED_MODULE_7__.SamProcessor),
-/* harmony export */   SpeechT5Processor: () => (/* reexport safe */ _speecht5_processing_speecht5_js__WEBPACK_IMPORTED_MODULE_8__.SpeechT5Processor),
-/* harmony export */   VLChatProcessor: () => (/* reexport safe */ _janus_processing_janus_js__WEBPACK_IMPORTED_MODULE_2__.VLChatProcessor),
-/* harmony export */   Wav2Vec2ProcessorWithLM: () => (/* reexport safe */ _wav2vec2_processing_wav2vec2_js__WEBPACK_IMPORTED_MODULE_9__.Wav2Vec2ProcessorWithLM),
-/* harmony export */   WhisperProcessor: () => (/* reexport safe */ _whisper_processing_whisper_js__WEBPACK_IMPORTED_MODULE_10__.WhisperProcessor)
+/* harmony export */   OwlViTProcessor: () => (/* reexport safe */ _owlvit_processing_owlvit_js__WEBPACK_IMPORTED_MODULE_5__.OwlViTProcessor),
+/* harmony export */   PaliGemmaProcessor: () => (/* reexport safe */ _paligemma_processing_paligemma_js__WEBPACK_IMPORTED_MODULE_6__.PaliGemmaProcessor),
+/* harmony export */   PyAnnoteProcessor: () => (/* reexport safe */ _pyannote_processing_pyannote_js__WEBPACK_IMPORTED_MODULE_7__.PyAnnoteProcessor),
+/* harmony export */   Qwen2VLProcessor: () => (/* reexport safe */ _qwen2_vl_processing_qwen2_vl_js__WEBPACK_IMPORTED_MODULE_8__.Qwen2VLProcessor),
+/* harmony export */   SamProcessor: () => (/* reexport safe */ _sam_processing_sam_js__WEBPACK_IMPORTED_MODULE_9__.SamProcessor),
+/* harmony export */   SpeechT5Processor: () => (/* reexport safe */ _speecht5_processing_speecht5_js__WEBPACK_IMPORTED_MODULE_10__.SpeechT5Processor),
+/* harmony export */   VLChatProcessor: () => (/* reexport safe */ _janus_processing_janus_js__WEBPACK_IMPORTED_MODULE_3__.VLChatProcessor),
+/* harmony export */   Wav2Vec2ProcessorWithLM: () => (/* reexport safe */ _wav2vec2_processing_wav2vec2_js__WEBPACK_IMPORTED_MODULE_11__.Wav2Vec2ProcessorWithLM),
+/* harmony export */   WhisperProcessor: () => (/* reexport safe */ _whisper_processing_whisper_js__WEBPACK_IMPORTED_MODULE_12__.WhisperProcessor)
 /* harmony export */ });
 /* harmony import */ var _florence2_processing_florence2_js__WEBPACK_IMPORTED_MODULE_0__ = __webpack_require__(/*! ./florence2/processing_florence2.js */ "./src/models/florence2/processing_florence2.js");
 /* harmony import */ var _mgp_str_processing_mgp_str_js__WEBPACK_IMPORTED_MODULE_1__ = __webpack_require__(/*! ./mgp_str/processing_mgp_str.js */ "./src/models/mgp_str/processing_mgp_str.js");
-/* harmony import */ var _janus_processing_janus_js__WEBPACK_IMPORTED_MODULE_2__ = __webpack_require__(/*! ./janus/processing_janus.js */ "./src/models/janus/processing_janus.js");
-/* harmony import */ var _jina_clip_processing_jina_clip_js__WEBPACK_IMPORTED_MODULE_3__ = __webpack_require__(/*! ./jina_clip/processing_jina_clip.js */ "./src/models/jina_clip/processing_jina_clip.js");
-/* harmony import */ var _owlvit_processing_owlvit_js__WEBPACK_IMPORTED_MODULE_4__ = __webpack_require__(/*! ./owlvit/processing_owlvit.js */ "./src/models/owlvit/processing_owlvit.js");
-/* harmony import */ var _pyannote_processing_pyannote_js__WEBPACK_IMPORTED_MODULE_5__ = __webpack_require__(/*! ./pyannote/processing_pyannote.js */ "./src/models/pyannote/processing_pyannote.js");
-/* harmony import */ var _qwen2_vl_processing_qwen2_vl_js__WEBPACK_IMPORTED_MODULE_6__ = __webpack_require__(/*! ./qwen2_vl/processing_qwen2_vl.js */ "./src/models/qwen2_vl/processing_qwen2_vl.js");
-/* harmony import */ var _sam_processing_sam_js__WEBPACK_IMPORTED_MODULE_7__ = __webpack_require__(/*! ./sam/processing_sam.js */ "./src/models/sam/processing_sam.js");
-/* harmony import */ var _speecht5_processing_speecht5_js__WEBPACK_IMPORTED_MODULE_8__ = __webpack_require__(/*! ./speecht5/processing_speecht5.js */ "./src/models/speecht5/processing_speecht5.js");
-/* harmony import */ var _wav2vec2_processing_wav2vec2_js__WEBPACK_IMPORTED_MODULE_9__ = __webpack_require__(/*! ./wav2vec2/processing_wav2vec2.js */ "./src/models/wav2vec2/processing_wav2vec2.js");
-/* harmony import */ var _whisper_processing_whisper_js__WEBPACK_IMPORTED_MODULE_10__ = __webpack_require__(/*! ./whisper/processing_whisper.js */ "./src/models/whisper/processing_whisper.js");
+/* harmony import */ var _idefics3_processing_idefics3_js__WEBPACK_IMPORTED_MODULE_2__ = __webpack_require__(/*! ./idefics3/processing_idefics3.js */ "./src/models/idefics3/processing_idefics3.js");
+/* harmony import */ var _janus_processing_janus_js__WEBPACK_IMPORTED_MODULE_3__ = __webpack_require__(/*! ./janus/processing_janus.js */ "./src/models/janus/processing_janus.js");
+/* harmony import */ var _jina_clip_processing_jina_clip_js__WEBPACK_IMPORTED_MODULE_4__ = __webpack_require__(/*! ./jina_clip/processing_jina_clip.js */ "./src/models/jina_clip/processing_jina_clip.js");
+/* harmony import */ var _owlvit_processing_owlvit_js__WEBPACK_IMPORTED_MODULE_5__ = __webpack_require__(/*! ./owlvit/processing_owlvit.js */ "./src/models/owlvit/processing_owlvit.js");
+/* harmony import */ var _paligemma_processing_paligemma_js__WEBPACK_IMPORTED_MODULE_6__ = __webpack_require__(/*! ./paligemma/processing_paligemma.js */ "./src/models/paligemma/processing_paligemma.js");
+/* harmony import */ var _pyannote_processing_pyannote_js__WEBPACK_IMPORTED_MODULE_7__ = __webpack_require__(/*! ./pyannote/processing_pyannote.js */ "./src/models/pyannote/processing_pyannote.js");
+/* harmony import */ var _qwen2_vl_processing_qwen2_vl_js__WEBPACK_IMPORTED_MODULE_8__ = __webpack_require__(/*! ./qwen2_vl/processing_qwen2_vl.js */ "./src/models/qwen2_vl/processing_qwen2_vl.js");
+/* harmony import */ var _sam_processing_sam_js__WEBPACK_IMPORTED_MODULE_9__ = __webpack_require__(/*! ./sam/processing_sam.js */ "./src/models/sam/processing_sam.js");
+/* harmony import */ var _speecht5_processing_speecht5_js__WEBPACK_IMPORTED_MODULE_10__ = __webpack_require__(/*! ./speecht5/processing_speecht5.js */ "./src/models/speecht5/processing_speecht5.js");
+/* harmony import */ var _wav2vec2_processing_wav2vec2_js__WEBPACK_IMPORTED_MODULE_11__ = __webpack_require__(/*! ./wav2vec2/processing_wav2vec2.js */ "./src/models/wav2vec2/processing_wav2vec2.js");
+/* harmony import */ var _whisper_processing_whisper_js__WEBPACK_IMPORTED_MODULE_12__ = __webpack_require__(/*! ./whisper/processing_whisper.js */ "./src/models/whisper/processing_whisper.js");
+
+
 
 
 
@@ -25537,6 +26188,12 @@ class PreTrainedTokenizer extends _utils_generic_js__WEBPACK_IMPORTED_MODULE_0__
         this.unk_token = this.getToken('unk_token');
         this.unk_token_id = this.model.tokens_to_ids.get(this.unk_token);
 
+        this.bos_token = this.getToken('bos_token');
+        this.bos_token_id = this.model.tokens_to_ids.get(this.bos_token);
+
+        this.eos_token = this.getToken('eos_token');
+        this.eos_token_id = this.model.tokens_to_ids.get(this.eos_token);
+
         this.model_max_length = tokenizerConfig.model_max_length;
 
         /** @type {boolean} Whether or not to strip the text when tokenizing (removing excess spaces before and after the string). */
@@ -26509,6 +27166,11 @@ class WhisperTokenizer extends PreTrainedTokenizer {
         let chunk = new_chunk();
         let time_offset = 0.0;
         const timestamp_begin = this.timestamp_begin;
+        // Whisper timestamp tokens start from 0.00 and go to timestamp 30.00 in 0.02 increments. 
+        // We can calculate the last time stamp token as timestamp_begin plus the number of tokens 
+        // tokens from 0.00 to 30.00 which is 1500. 
+        const total_timestamp_tokens = 1500; // (30.00 - 0.00) / 0.02
+        const timestamp_end = timestamp_begin + total_timestamp_tokens;
 
         let previous_tokens = [];
         let previous_token_timestamps = [];
@@ -26596,7 +27258,7 @@ class WhisperTokenizer extends PreTrainedTokenizer {
                     } else {
                         // 2/ This is a regular special token, ignoring it
                     }
-                } else if (token >= timestamp_begin) {
+                } else if (token >= timestamp_begin && token <= timestamp_end) {
                     // 3/ Timestamp token
                     const time = (token - timestamp_begin) * time_precision + time_offset;
                     const rounded_time = (0,_utils_maths_js__WEBPACK_IMPORTED_MODULE_3__.round)(time, 2);
@@ -28061,6 +28723,7 @@ __webpack_require__.r(__webpack_exports__);
 /* harmony export */ __webpack_require__.d(__webpack_exports__, {
 /* harmony export */   calculateDimensions: () => (/* binding */ calculateDimensions),
 /* harmony export */   calculateReflectOffset: () => (/* binding */ calculateReflectOffset),
+/* harmony export */   count: () => (/* binding */ count),
 /* harmony export */   dispatchCallback: () => (/* binding */ dispatchCallback),
 /* harmony export */   escapeRegExp: () => (/* binding */ escapeRegExp),
 /* harmony export */   isIntegralNumber: () => (/* binding */ isIntegralNumber),
@@ -28084,15 +28747,45 @@ __webpack_require__.r(__webpack_exports__);
  */
 
 /**
- * @typedef {Object} ProgressInfo
- * @property {'initiate' | 'download' | 'progress' | 'done'} status The status of the progress item.
- * @property {string} name This can be either:
- * - a string, the *model id* of a model repo on huggingface.co.
- * - a path to a *directory* potentially containing the file.
- * @property {string} file The name of the file
- * @property {number} [progress] A number between 0 and 100. Only available for the 'progress' status.
- * @property {number} [loaded] The number of bytes loaded. Only available for the 'progress' status.
- * @property {number} [total] The total number of bytes to be loaded. Only available for the 'progress' status.
+ * @typedef {Object} InitiateProgressInfo
+ * @property {'initiate'} status
+ * @property {string} name The model id or directory path.
+ * @property {string} file The name of the file.
+ */
+
+/**
+ * @typedef {Object} DownloadProgressInfo
+ * @property {'download'} status
+ * @property {string} name The model id or directory path.
+ * @property {string} file The name of the file.
+ */
+
+/**
+ * @typedef {Object} ProgressStatusInfo
+ * @property {'progress'} status
+ * @property {string} name The model id or directory path.
+ * @property {string} file The name of the file.
+ * @property {number} progress A number between 0 and 100.
+ * @property {number} loaded The number of bytes loaded.
+ * @property {number} total The total number of bytes to be loaded.
+ */
+
+/**
+ * @typedef {Object} DoneProgressInfo
+ * @property {'done'} status
+ * @property {string} name The model id or directory path.
+ * @property {string} file The name of the file.
+ */
+
+/**
+ * @typedef {Object} ReadyProgressInfo
+ * @property {'ready'} status
+ * @property {string} task The loaded task.
+ * @property {string} model The loaded model.
+ */
+
+/**
+ * @typedef {InitiateProgressInfo | DownloadProgressInfo | ProgressStatusInfo | DoneProgressInfo | ReadyProgressInfo} ProgressInfo
  */
 
 /**
@@ -28263,6 +28956,20 @@ function len(s) {
     return length;
 }
 
+/**
+ * Count the occurrences of a value in an array or string.
+ * This mimics the behavior of Python's `count` method.
+ * @param {any[]|string} arr The array or string to search.
+ * @param {any} value The value to count.
+ */
+function count(arr, value) {
+    let count = 0;
+    for (const v of arr) {
+        if (v === value) ++count;
+    }
+    return count;
+}
+
 
 /***/ }),
 
@@ -28813,6 +29520,7 @@ const isWebGpuFp16Supported = (function () {
 })();
 
 const DATA_TYPES = Object.freeze({
+    auto: 'auto', // Auto-detect based on environment
     fp32: 'fp32',
     fp16: 'fp16',
     q8: 'q8',
@@ -28829,7 +29537,7 @@ const DEFAULT_DEVICE_DTYPE_MAPPING = Object.freeze({
     [_devices_js__WEBPACK_IMPORTED_MODULE_1__.DEVICE_TYPES.wasm]: DATA_TYPES.q8,
 });
 
-/** @type {Record<DataType, string>} */
+/** @type {Record<Exclude<DataType, "auto">, string>} */
 const DEFAULT_DTYPE_SUFFIX_MAPPING = Object.freeze({
     [DATA_TYPES.fp32]: '',
     [DATA_TYPES.fp16]: '_fp16',
@@ -29415,13 +30123,6 @@ async function getModelFile(path_or_repo_id, filename, fatal = true, options = {
         file: filename
     })
 
-    /** @type {import('./core.js').ProgressInfo} */
-    const progressInfo = {
-        status: 'progress',
-        name: path_or_repo_id,
-        file: filename
-    }
-
     /** @type {Uint8Array} */
     let buffer;
 
@@ -29441,7 +30142,9 @@ async function getModelFile(path_or_repo_id, filename, fatal = true, options = {
 
         // For completeness, we still fire the final progress callback
         (0,_core_js__WEBPACK_IMPORTED_MODULE_3__.dispatchCallback)(options.progress_callback, {
-            ...progressInfo,
+            status: 'progress',
+            name: path_or_repo_id,
+            file: filename,
             progress: 100,
             loaded: buffer.length,
             total: buffer.length,
@@ -29449,7 +30152,9 @@ async function getModelFile(path_or_repo_id, filename, fatal = true, options = {
     } else {
         buffer = await readResponse(response, data => {
             (0,_core_js__WEBPACK_IMPORTED_MODULE_3__.dispatchCallback)(options.progress_callback, {
-                ...progressInfo,
+                status: 'progress',
+                name: path_or_repo_id,
+                file: filename,
                 ...data,
             })
         })
@@ -29506,12 +30211,11 @@ async function getModelJSON(modelPath, fileName, fatal = true, options = {}) {
 
     return JSON.parse(jsonData);
 }
-
 /**
  * Read and track progress when reading a Response object
  *
- * @param {any} response The Response object to read
- * @param {function} progress_callback The function to call with progress updates
+ * @param {Response|FileResponse} response The Response object to read
+ * @param {(data: {progress: number, loaded: number, total: number}) => void} progress_callback The function to call with progress updates
  * @returns {Promise<Uint8Array>} A Promise that resolves with the Uint8Array buffer
  */
 async function readResponse(response, progress_callback) {
@@ -29594,7 +30298,8 @@ function pathJoin(...parts) {
 
 __webpack_require__.r(__webpack_exports__);
 /* harmony export */ __webpack_require__.d(__webpack_exports__, {
-/* harmony export */   RawImage: () => (/* binding */ RawImage)
+/* harmony export */   RawImage: () => (/* binding */ RawImage),
+/* harmony export */   load_image: () => (/* binding */ load_image)
 /* harmony export */ });
 /* harmony import */ var _core_js__WEBPACK_IMPORTED_MODULE_0__ = __webpack_require__(/*! ./core.js */ "./src/utils/core.js");
 /* harmony import */ var _hub_js__WEBPACK_IMPORTED_MODULE_1__ = __webpack_require__(/*! ./hub.js */ "./src/utils/hub.js");
@@ -29619,13 +30324,11 @@ __webpack_require__.r(__webpack_exports__);
 // Will be empty (or not used) if running in browser or web-worker
 
 
-const BROWSER_ENV = typeof self !== 'undefined';
-const WEBWORKER_ENV = BROWSER_ENV && self.constructor.name === 'DedicatedWorkerGlobalScope';
-
 let createCanvasFunction;
 let ImageDataClass;
 let loadImageFunction;
-if (BROWSER_ENV) {
+const IS_BROWSER_OR_WEBWORKER = _env_js__WEBPACK_IMPORTED_MODULE_2__.apis.IS_BROWSER_ENV || _env_js__WEBPACK_IMPORTED_MODULE_2__.apis.IS_WEBWORKER_ENV;
+if (IS_BROWSER_OR_WEBWORKER) {
     // Running in browser or web-worker
     createCanvasFunction = (/** @type {number} */ width, /** @type {number} */ height) => {
         if (!self.OffscreenCanvas) {
@@ -29735,7 +30438,7 @@ class RawImage {
      * @returns {RawImage} The image object.
      */
     static fromCanvas(canvas) {
-        if (!BROWSER_ENV) {
+        if (!IS_BROWSER_OR_WEBWORKER) {
             throw new Error('fromCanvas() is only supported in browser environments.')
         }
 
@@ -29764,7 +30467,7 @@ class RawImage {
      * @returns {Promise<RawImage>} The image object.
      */
     static async fromBlob(blob) {
-        if (BROWSER_ENV) {
+        if (IS_BROWSER_OR_WEBWORKER) {
             // Running in environment with canvas
             const img = await loadImageFunction(blob);
 
@@ -29908,6 +30611,46 @@ class RawImage {
         return this._update(newData, this.width, this.height, 4);
     }
 
+    /**
+     * Apply an alpha mask to the image. Operates in place.
+     * @param {RawImage} mask The mask to apply. It should have a single channel.
+     * @returns {RawImage} The masked image.
+     * @throws {Error} If the mask is not the same size as the image.
+     * @throws {Error} If the image does not have 4 channels.
+     * @throws {Error} If the mask is not a single channel.
+     */
+    putAlpha(mask) {
+        if (mask.width !== this.width || mask.height !== this.height) {
+            throw new Error(`Expected mask size to be ${this.width}x${this.height}, but got ${mask.width}x${mask.height}`);
+        }
+        if (mask.channels !== 1) {
+            throw new Error(`Expected mask to have 1 channel, but got ${mask.channels}`);
+        }
+
+        const this_data = this.data;
+        const mask_data = mask.data;
+        const num_pixels = this.width * this.height;
+        if (this.channels === 3) {
+            // Convert to RGBA and simultaneously apply mask to alpha channel
+            const newData = new Uint8ClampedArray(num_pixels * 4);
+            for (let i = 0, in_offset = 0, out_offset = 0; i < num_pixels; ++i) {
+                newData[out_offset++] = this_data[in_offset++];
+                newData[out_offset++] = this_data[in_offset++];
+                newData[out_offset++] = this_data[in_offset++];
+                newData[out_offset++] = mask_data[i];
+            }
+            return this._update(newData, this.width, this.height, 4);
+
+        } else if (this.channels === 4) {
+            // Apply mask to alpha channel in place
+            for (let i = 0; i < num_pixels; ++i) {
+                this_data[4 * i + 3] = mask_data[i];
+            }
+            return this;
+        }
+        throw new Error(`Expected image to have 3 or 4 channels, but got ${this.channels}`);
+    }
+
     /**
      * Resize the image to the given dimensions. This method uses the canvas API to perform the resizing.
      * @param {number} width The width of the new image. `null` or `-1` will preserve the aspect ratio.
@@ -29942,7 +30685,7 @@ class RawImage {
             height = (width / this.width) * this.height;
         }
 
-        if (BROWSER_ENV) {
+        if (IS_BROWSER_OR_WEBWORKER) {
             // TODO use `resample` in browser environment
 
             // Store number of channels before resizing
@@ -30015,7 +30758,7 @@ class RawImage {
             return this;
         }
 
-        if (BROWSER_ENV) {
+        if (IS_BROWSER_OR_WEBWORKER) {
             // Store number of channels before padding
             const numChannels = this.channels;
 
@@ -30064,7 +30807,7 @@ class RawImage {
         const crop_width = x_max - x_min + 1;
         const crop_height = y_max - y_min + 1;
 
-        if (BROWSER_ENV) {
+        if (IS_BROWSER_OR_WEBWORKER) {
             // Store number of channels before resizing
             const numChannels = this.channels;
 
@@ -30112,7 +30855,7 @@ class RawImage {
         const height_offset = (this.height - crop_height) / 2;
 
 
-        if (BROWSER_ENV) {
+        if (IS_BROWSER_OR_WEBWORKER) {
             // Store number of channels before resizing
             const numChannels = this.channels;
 
@@ -30217,7 +30960,7 @@ class RawImage {
     }
 
     async toBlob(type = 'image/png', quality = 1) {
-        if (!BROWSER_ENV) {
+        if (!IS_BROWSER_OR_WEBWORKER) {
             throw new Error('toBlob() is only supported in browser environments.')
         }
 
@@ -30243,7 +30986,7 @@ class RawImage {
     }
 
     toCanvas() {
-        if (!BROWSER_ENV) {
+        if (!IS_BROWSER_OR_WEBWORKER) {
             throw new Error('toCanvas() is only supported in browser environments.')
         }
 
@@ -30347,8 +31090,8 @@ class RawImage {
      */
     async save(path) {
 
-        if (BROWSER_ENV) {
-            if (WEBWORKER_ENV) {
+        if (IS_BROWSER_OR_WEBWORKER) {
+            if (_env_js__WEBPACK_IMPORTED_MODULE_2__.apis.IS_WEBWORKER_ENV) {
                 throw new Error('Unable to save an image from a Web Worker.')
             }
 
@@ -30384,7 +31127,7 @@ class RawImage {
     }
 
     toSharp() {
-        if (BROWSER_ENV) {
+        if (IS_BROWSER_OR_WEBWORKER) {
             throw new Error('toSharp() is only supported in server-side environments.')
         }
 
@@ -30398,6 +31141,11 @@ class RawImage {
     }
 }
 
+/**
+ * Helper function to load an image from a URL, path, etc.
+ */
+const load_image = RawImage.read.bind(RawImage);
+
 
 /***/ }),
 
@@ -31548,6 +32296,8 @@ const DataTypeMap = Object.freeze({
     int64: BigInt64Array,
     uint64: BigUint64Array,
     bool: Uint8Array,
+    uint4: Uint8Array,
+    int4: Int8Array,
 });
 
 /**
@@ -32869,7 +33619,7 @@ function fullHelper(size, fill_value, dtype, cls) {
 /**
  * Creates a tensor of size size filled with fill_value. The tensor's dtype is inferred from fill_value.
  * @param {number[]} size A sequence of integers defining the shape of the output tensor.
- * @param {number|bigint} fill_value The value to fill the output tensor with.
+ * @param {number|bigint|boolean} fill_value The value to fill the output tensor with.
  * @returns {Tensor} The filled tensor.
  */
 function full(size, fill_value) {
@@ -32881,6 +33631,9 @@ function full(size, fill_value) {
     } else if (typeof fill_value === 'bigint') {
         dtype = 'int64';
         typedArrayCls = BigInt64Array;
+    } else if (typeof fill_value === 'boolean') {
+        dtype = 'bool';
+        typedArrayCls = Uint8Array;
     } else {
         // TODO: support other dtypes
         throw new Error(`Unsupported data type: ${typeof fill_value}`);
@@ -33062,6 +33815,8 @@ function quantize_embeddings(tensor, precision) {
 /******/ 
 /************************************************************************/
 var __webpack_exports__ = {};
+// This entry needs to be wrapped in an IIFE because it needs to be isolated against other modules in the chunk.
+(() => {
 /*!*****************************!*\
   !*** ./src/transformers.js ***!
   \*****************************/
@@ -33328,6 +34083,13 @@ __webpack_require__.r(__webpack_exports__);
 /* harmony export */   HubertForSequenceClassification: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.HubertForSequenceClassification),
 /* harmony export */   HubertModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.HubertModel),
 /* harmony export */   HubertPreTrainedModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.HubertPreTrainedModel),
+/* harmony export */   IJepaForImageClassification: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.IJepaForImageClassification),
+/* harmony export */   IJepaModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.IJepaModel),
+/* harmony export */   IJepaPreTrainedModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.IJepaPreTrainedModel),
+/* harmony export */   Idefics3ForConditionalGeneration: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.Idefics3ForConditionalGeneration),
+/* harmony export */   Idefics3ImageProcessor: () => (/* reexport safe */ _models_image_processors_js__WEBPACK_IMPORTED_MODULE_13__.Idefics3ImageProcessor),
+/* harmony export */   Idefics3PreTrainedModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.Idefics3PreTrainedModel),
+/* harmony export */   Idefics3Processor: () => (/* reexport safe */ _models_processors_js__WEBPACK_IMPORTED_MODULE_16__.Idefics3Processor),
 /* harmony export */   ImageClassificationPipeline: () => (/* reexport safe */ _pipelines_js__WEBPACK_IMPORTED_MODULE_1__.ImageClassificationPipeline),
 /* harmony export */   ImageFeatureExtractionPipeline: () => (/* reexport safe */ _pipelines_js__WEBPACK_IMPORTED_MODULE_1__.ImageFeatureExtractionPipeline),
 /* harmony export */   ImageFeatureExtractor: () => (/* reexport safe */ _models_feature_extractors_js__WEBPACK_IMPORTED_MODULE_10__.ImageFeatureExtractor),
@@ -33462,6 +34224,9 @@ __webpack_require__.r(__webpack_exports__);
 /* harmony export */   OPTModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.OPTModel),
 /* harmony export */   OPTPreTrainedModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.OPTPreTrainedModel),
 /* harmony export */   ObjectDetectionPipeline: () => (/* reexport safe */ _pipelines_js__WEBPACK_IMPORTED_MODULE_1__.ObjectDetectionPipeline),
+/* harmony export */   Olmo2ForCausalLM: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.Olmo2ForCausalLM),
+/* harmony export */   Olmo2Model: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.Olmo2Model),
+/* harmony export */   Olmo2PreTrainedModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.Olmo2PreTrainedModel),
 /* harmony export */   OlmoForCausalLM: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.OlmoForCausalLM),
 /* harmony export */   OlmoModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.OlmoModel),
 /* harmony export */   OlmoPreTrainedModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.OlmoPreTrainedModel),
@@ -33478,6 +34243,9 @@ __webpack_require__.r(__webpack_exports__);
 /* harmony export */   Owlv2ImageProcessor: () => (/* reexport safe */ _models_image_processors_js__WEBPACK_IMPORTED_MODULE_13__.Owlv2ImageProcessor),
 /* harmony export */   Owlv2Model: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.Owlv2Model),
 /* harmony export */   Owlv2PreTrainedModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.Owlv2PreTrainedModel),
+/* harmony export */   PaliGemmaForConditionalGeneration: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.PaliGemmaForConditionalGeneration),
+/* harmony export */   PaliGemmaPreTrainedModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.PaliGemmaPreTrainedModel),
+/* harmony export */   PaliGemmaProcessor: () => (/* reexport safe */ _models_processors_js__WEBPACK_IMPORTED_MODULE_16__.PaliGemmaProcessor),
 /* harmony export */   PatchTSMixerForPrediction: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.PatchTSMixerForPrediction),
 /* harmony export */   PatchTSMixerModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.PatchTSMixerModel),
 /* harmony export */   PatchTSMixerPreTrainedModel: () => (/* reexport safe */ _models_js__WEBPACK_IMPORTED_MODULE_2__.PatchTSMixerPreTrainedModel),
@@ -33719,6 +34487,7 @@ __webpack_require__.r(__webpack_exports__);
 /* harmony export */   interpolate_data: () => (/* reexport safe */ _utils_maths_js__WEBPACK_IMPORTED_MODULE_8__.interpolate_data),
 /* harmony export */   is_chinese_char: () => (/* reexport safe */ _tokenizers_js__WEBPACK_IMPORTED_MODULE_3__.is_chinese_char),
 /* harmony export */   layer_norm: () => (/* reexport safe */ _utils_tensor_js__WEBPACK_IMPORTED_MODULE_7__.layer_norm),
+/* harmony export */   load_image: () => (/* reexport safe */ _utils_image_js__WEBPACK_IMPORTED_MODULE_6__.load_image),
 /* harmony export */   log_softmax: () => (/* reexport safe */ _utils_maths_js__WEBPACK_IMPORTED_MODULE_8__.log_softmax),
 /* harmony export */   magnitude: () => (/* reexport safe */ _utils_maths_js__WEBPACK_IMPORTED_MODULE_8__.magnitude),
 /* harmony export */   matmul: () => (/* reexport safe */ _utils_tensor_js__WEBPACK_IMPORTED_MODULE_7__.matmul),
@@ -33808,6 +34577,8 @@ __webpack_require__.r(__webpack_exports__);
 
 
 
+
+})();
 
 var __webpack_exports__ASTFeatureExtractor = __webpack_exports__.ASTFeatureExtractor;
 var __webpack_exports__ASTForAudioClassification = __webpack_exports__.ASTForAudioClassification;
@@ -34070,6 +34841,13 @@ var __webpack_exports__HubertForCTC = __webpack_exports__.HubertForCTC;
 var __webpack_exports__HubertForSequenceClassification = __webpack_exports__.HubertForSequenceClassification;
 var __webpack_exports__HubertModel = __webpack_exports__.HubertModel;
 var __webpack_exports__HubertPreTrainedModel = __webpack_exports__.HubertPreTrainedModel;
+var __webpack_exports__IJepaForImageClassification = __webpack_exports__.IJepaForImageClassification;
+var __webpack_exports__IJepaModel = __webpack_exports__.IJepaModel;
+var __webpack_exports__IJepaPreTrainedModel = __webpack_exports__.IJepaPreTrainedModel;
+var __webpack_exports__Idefics3ForConditionalGeneration = __webpack_exports__.Idefics3ForConditionalGeneration;
+var __webpack_exports__Idefics3ImageProcessor = __webpack_exports__.Idefics3ImageProcessor;
+var __webpack_exports__Idefics3PreTrainedModel = __webpack_exports__.Idefics3PreTrainedModel;
+var __webpack_exports__Idefics3Processor = __webpack_exports__.Idefics3Processor;
 var __webpack_exports__ImageClassificationPipeline = __webpack_exports__.ImageClassificationPipeline;
 var __webpack_exports__ImageFeatureExtractionPipeline = __webpack_exports__.ImageFeatureExtractionPipeline;
 var __webpack_exports__ImageFeatureExtractor = __webpack_exports__.ImageFeatureExtractor;
@@ -34204,6 +34982,9 @@ var __webpack_exports__OPTForCausalLM = __webpack_exports__.OPTForCausalLM;
 var __webpack_exports__OPTModel = __webpack_exports__.OPTModel;
 var __webpack_exports__OPTPreTrainedModel = __webpack_exports__.OPTPreTrainedModel;
 var __webpack_exports__ObjectDetectionPipeline = __webpack_exports__.ObjectDetectionPipeline;
+var __webpack_exports__Olmo2ForCausalLM = __webpack_exports__.Olmo2ForCausalLM;
+var __webpack_exports__Olmo2Model = __webpack_exports__.Olmo2Model;
+var __webpack_exports__Olmo2PreTrainedModel = __webpack_exports__.Olmo2PreTrainedModel;
 var __webpack_exports__OlmoForCausalLM = __webpack_exports__.OlmoForCausalLM;
 var __webpack_exports__OlmoModel = __webpack_exports__.OlmoModel;
 var __webpack_exports__OlmoPreTrainedModel = __webpack_exports__.OlmoPreTrainedModel;
@@ -34220,6 +35001,9 @@ var __webpack_exports__Owlv2ForObjectDetection = __webpack_exports__.Owlv2ForObj
 var __webpack_exports__Owlv2ImageProcessor = __webpack_exports__.Owlv2ImageProcessor;
 var __webpack_exports__Owlv2Model = __webpack_exports__.Owlv2Model;
 var __webpack_exports__Owlv2PreTrainedModel = __webpack_exports__.Owlv2PreTrainedModel;
+var __webpack_exports__PaliGemmaForConditionalGeneration = __webpack_exports__.PaliGemmaForConditionalGeneration;
+var __webpack_exports__PaliGemmaPreTrainedModel = __webpack_exports__.PaliGemmaPreTrainedModel;
+var __webpack_exports__PaliGemmaProcessor = __webpack_exports__.PaliGemmaProcessor;
 var __webpack_exports__PatchTSMixerForPrediction = __webpack_exports__.PatchTSMixerForPrediction;
 var __webpack_exports__PatchTSMixerModel = __webpack_exports__.PatchTSMixerModel;
 var __webpack_exports__PatchTSMixerPreTrainedModel = __webpack_exports__.PatchTSMixerPreTrainedModel;
@@ -34461,6 +35245,7 @@ var __webpack_exports__interpolate_4d = __webpack_exports__.interpolate_4d;
 var __webpack_exports__interpolate_data = __webpack_exports__.interpolate_data;
 var __webpack_exports__is_chinese_char = __webpack_exports__.is_chinese_char;
 var __webpack_exports__layer_norm = __webpack_exports__.layer_norm;
+var __webpack_exports__load_image = __webpack_exports__.load_image;
 var __webpack_exports__log_softmax = __webpack_exports__.log_softmax;
 var __webpack_exports__magnitude = __webpack_exports__.magnitude;
 var __webpack_exports__matmul = __webpack_exports__.matmul;
@@ -34487,6 +35272,6 @@ var __webpack_exports__topk = __webpack_exports__.topk;
 var __webpack_exports__window_function = __webpack_exports__.window_function;
 var __webpack_exports__zeros = __webpack_exports__.zeros;
 var __webpack_exports__zeros_like = __webpack_exports__.zeros_like;
-export { __webpack_exports__ASTFeatureExtractor as ASTFeatureExtractor, __webpack_exports__ASTForAudioClassification as ASTForAudioClassification, __webpack_exports__ASTModel as ASTModel, __webpack_exports__ASTPreTrainedModel as ASTPreTrainedModel, __webpack_exports__AlbertForMaskedLM as AlbertForMaskedLM, __webpack_exports__AlbertForQuestionAnswering as AlbertForQuestionAnswering, __webpack_exports__AlbertForSequenceClassification as AlbertForSequenceClassification, __webpack_exports__AlbertModel as AlbertModel, __webpack_exports__AlbertPreTrainedModel as AlbertPreTrainedModel, __webpack_exports__AlbertTokenizer as AlbertTokenizer, __webpack_exports__AudioClassificationPipeline as AudioClassificationPipeline, __webpack_exports__AutoConfig as AutoConfig, __webpack_exports__AutoFeatureExtractor as AutoFeatureExtractor, __webpack_exports__AutoImageProcessor as AutoImageProcessor, __webpack_exports__AutoModel as AutoModel, __webpack_exports__AutoModelForAudioClassification as AutoModelForAudioClassification, __webpack_exports__AutoModelForAudioFrameClassification as AutoModelForAudioFrameClassification, __webpack_exports__AutoModelForCTC as AutoModelForCTC, __webpack_exports__AutoModelForCausalLM as AutoModelForCausalLM, __webpack_exports__AutoModelForDepthEstimation as AutoModelForDepthEstimation, __webpack_exports__AutoModelForDocumentQuestionAnswering as AutoModelForDocumentQuestionAnswering, __webpack_exports__AutoModelForImageClassification as AutoModelForImageClassification, __webpack_exports__AutoModelForImageFeatureExtraction as AutoModelForImageFeatureExtraction, __webpack_exports__AutoModelForImageMatting as AutoModelForImageMatting, __webpack_exports__AutoModelForImageSegmentation as AutoModelForImageSegmentation, __webpack_exports__AutoModelForImageToImage as AutoModelForImageToImage, __webpack_exports__AutoModelForMaskGeneration as AutoModelForMaskGeneration, __webpack_exports__AutoModelForMaskedLM as AutoModelForMaskedLM, __webpack_exports__AutoModelForNormalEstimation as AutoModelForNormalEstimation, __webpack_exports__AutoModelForObjectDetection as AutoModelForObjectDetection, __webpack_exports__AutoModelForPoseEstimation as AutoModelForPoseEstimation, __webpack_exports__AutoModelForQuestionAnswering as AutoModelForQuestionAnswering, __webpack_exports__AutoModelForSemanticSegmentation as AutoModelForSemanticSegmentation, __webpack_exports__AutoModelForSeq2SeqLM as AutoModelForSeq2SeqLM, __webpack_exports__AutoModelForSequenceClassification as AutoModelForSequenceClassification, __webpack_exports__AutoModelForSpeechSeq2Seq as AutoModelForSpeechSeq2Seq, __webpack_exports__AutoModelForTextToSpectrogram as AutoModelForTextToSpectrogram, __webpack_exports__AutoModelForTextToWaveform as AutoModelForTextToWaveform, __webpack_exports__AutoModelForTokenClassification as AutoModelForTokenClassification, __webpack_exports__AutoModelForUniversalSegmentation as AutoModelForUniversalSegmentation, __webpack_exports__AutoModelForVision2Seq as AutoModelForVision2Seq, __webpack_exports__AutoModelForXVector as AutoModelForXVector, __webpack_exports__AutoModelForZeroShotObjectDetection as AutoModelForZeroShotObjectDetection, __webpack_exports__AutoProcessor as AutoProcessor, __webpack_exports__AutoTokenizer as AutoTokenizer, __webpack_exports__AutomaticSpeechRecognitionPipeline as AutomaticSpeechRecognitionPipeline, __webpack_exports__BartForConditionalGeneration as BartForConditionalGeneration, __webpack_exports__BartForSequenceClassification as BartForSequenceClassification, __webpack_exports__BartModel as BartModel, __webpack_exports__BartPretrainedModel as BartPretrainedModel, __webpack_exports__BartTokenizer as BartTokenizer, __webpack_exports__BaseModelOutput as BaseModelOutput, __webpack_exports__BaseStreamer as BaseStreamer, __webpack_exports__BeitFeatureExtractor as BeitFeatureExtractor, __webpack_exports__BeitForImageClassification as BeitForImageClassification, __webpack_exports__BeitModel as BeitModel, __webpack_exports__BeitPreTrainedModel as BeitPreTrainedModel, __webpack_exports__BertForMaskedLM as BertForMaskedLM, __webpack_exports__BertForQuestionAnswering as BertForQuestionAnswering, __webpack_exports__BertForSequenceClassification as BertForSequenceClassification, __webpack_exports__BertForTokenClassification as BertForTokenClassification, __webpack_exports__BertModel as BertModel, __webpack_exports__BertPreTrainedModel as BertPreTrainedModel, __webpack_exports__BertTokenizer as BertTokenizer, __webpack_exports__BitImageProcessor as BitImageProcessor, __webpack_exports__BlenderbotForConditionalGeneration as BlenderbotForConditionalGeneration, __webpack_exports__BlenderbotModel as BlenderbotModel, __webpack_exports__BlenderbotPreTrainedModel as BlenderbotPreTrainedModel, __webpack_exports__BlenderbotSmallForConditionalGeneration as BlenderbotSmallForConditionalGeneration, __webpack_exports__BlenderbotSmallModel as BlenderbotSmallModel, __webpack_exports__BlenderbotSmallPreTrainedModel as BlenderbotSmallPreTrainedModel, __webpack_exports__BlenderbotSmallTokenizer as BlenderbotSmallTokenizer, __webpack_exports__BlenderbotTokenizer as BlenderbotTokenizer, __webpack_exports__BloomForCausalLM as BloomForCausalLM, __webpack_exports__BloomModel as BloomModel, __webpack_exports__BloomPreTrainedModel as BloomPreTrainedModel, __webpack_exports__BloomTokenizer as BloomTokenizer, __webpack_exports__CLIPFeatureExtractor as CLIPFeatureExtractor, __webpack_exports__CLIPImageProcessor as CLIPImageProcessor, __webpack_exports__CLIPModel as CLIPModel, __webpack_exports__CLIPPreTrainedModel as CLIPPreTrainedModel, __webpack_exports__CLIPSegForImageSegmentation as CLIPSegForImageSegmentation, __webpack_exports__CLIPSegModel as CLIPSegModel, __webpack_exports__CLIPSegPreTrainedModel as CLIPSegPreTrainedModel, __webpack_exports__CLIPTextModel as CLIPTextModel, __webpack_exports__CLIPTextModelWithProjection as CLIPTextModelWithProjection, __webpack_exports__CLIPTokenizer as CLIPTokenizer, __webpack_exports__CLIPVisionModel as CLIPVisionModel, __webpack_exports__CLIPVisionModelWithProjection as CLIPVisionModelWithProjection, __webpack_exports__CamembertForMaskedLM as CamembertForMaskedLM, __webpack_exports__CamembertForQuestionAnswering as CamembertForQuestionAnswering, __webpack_exports__CamembertForSequenceClassification as CamembertForSequenceClassification, __webpack_exports__CamembertForTokenClassification as CamembertForTokenClassification, __webpack_exports__CamembertModel as CamembertModel, __webpack_exports__CamembertPreTrainedModel as CamembertPreTrainedModel, __webpack_exports__CamembertTokenizer as CamembertTokenizer, __webpack_exports__CausalLMOutput as CausalLMOutput, __webpack_exports__CausalLMOutputWithPast as CausalLMOutputWithPast, __webpack_exports__ChineseCLIPFeatureExtractor as ChineseCLIPFeatureExtractor, __webpack_exports__ChineseCLIPModel as ChineseCLIPModel, __webpack_exports__ChineseCLIPPreTrainedModel as ChineseCLIPPreTrainedModel, __webpack_exports__ClapAudioModelWithProjection as ClapAudioModelWithProjection, __webpack_exports__ClapFeatureExtractor as ClapFeatureExtractor, __webpack_exports__ClapModel as ClapModel, __webpack_exports__ClapPreTrainedModel as ClapPreTrainedModel, __webpack_exports__ClapTextModelWithProjection as ClapTextModelWithProjection, __webpack_exports__ClassifierFreeGuidanceLogitsProcessor as ClassifierFreeGuidanceLogitsProcessor, __webpack_exports__CodeGenForCausalLM as CodeGenForCausalLM, __webpack_exports__CodeGenModel as CodeGenModel, __webpack_exports__CodeGenPreTrainedModel as CodeGenPreTrainedModel, __webpack_exports__CodeGenTokenizer as CodeGenTokenizer, __webpack_exports__CodeLlamaTokenizer as CodeLlamaTokenizer, __webpack_exports__CohereForCausalLM as CohereForCausalLM, __webpack_exports__CohereModel as CohereModel, __webpack_exports__CoherePreTrainedModel as CoherePreTrainedModel, __webpack_exports__CohereTokenizer as CohereTokenizer, __webpack_exports__ConvBertForMaskedLM as ConvBertForMaskedLM, __webpack_exports__ConvBertForQuestionAnswering as ConvBertForQuestionAnswering, __webpack_exports__ConvBertForSequenceClassification as ConvBertForSequenceClassification, __webpack_exports__ConvBertForTokenClassification as ConvBertForTokenClassification, __webpack_exports__ConvBertModel as ConvBertModel, __webpack_exports__ConvBertPreTrainedModel as ConvBertPreTrainedModel, __webpack_exports__ConvBertTokenizer as ConvBertTokenizer, __webpack_exports__ConvNextFeatureExtractor as ConvNextFeatureExtractor, __webpack_exports__ConvNextForImageClassification as ConvNextForImageClassification, __webpack_exports__ConvNextImageProcessor as ConvNextImageProcessor, __webpack_exports__ConvNextModel as ConvNextModel, __webpack_exports__ConvNextPreTrainedModel as ConvNextPreTrainedModel, __webpack_exports__ConvNextV2ForImageClassification as ConvNextV2ForImageClassification, __webpack_exports__ConvNextV2Model as ConvNextV2Model, __webpack_exports__ConvNextV2PreTrainedModel as ConvNextV2PreTrainedModel, __webpack_exports__DPTFeatureExtractor as DPTFeatureExtractor, __webpack_exports__DPTForDepthEstimation as DPTForDepthEstimation, __webpack_exports__DPTImageProcessor as DPTImageProcessor, __webpack_exports__DPTModel as DPTModel, __webpack_exports__DPTPreTrainedModel as DPTPreTrainedModel, __webpack_exports__DebertaForMaskedLM as DebertaForMaskedLM, __webpack_exports__DebertaForQuestionAnswering as DebertaForQuestionAnswering, __webpack_exports__DebertaForSequenceClassification as DebertaForSequenceClassification, __webpack_exports__DebertaForTokenClassification as DebertaForTokenClassification, __webpack_exports__DebertaModel as DebertaModel, __webpack_exports__DebertaPreTrainedModel as DebertaPreTrainedModel, __webpack_exports__DebertaTokenizer as DebertaTokenizer, __webpack_exports__DebertaV2ForMaskedLM as DebertaV2ForMaskedLM, __webpack_exports__DebertaV2ForQuestionAnswering as DebertaV2ForQuestionAnswering, __webpack_exports__DebertaV2ForSequenceClassification as DebertaV2ForSequenceClassification, __webpack_exports__DebertaV2ForTokenClassification as DebertaV2ForTokenClassification, __webpack_exports__DebertaV2Model as DebertaV2Model, __webpack_exports__DebertaV2PreTrainedModel as DebertaV2PreTrainedModel, __webpack_exports__DebertaV2Tokenizer as DebertaV2Tokenizer, __webpack_exports__DecisionTransformerModel as DecisionTransformerModel, __webpack_exports__DecisionTransformerPreTrainedModel as DecisionTransformerPreTrainedModel, __webpack_exports__DeiTFeatureExtractor as DeiTFeatureExtractor, __webpack_exports__DeiTForImageClassification as DeiTForImageClassification, __webpack_exports__DeiTImageProcessor as DeiTImageProcessor, __webpack_exports__DeiTModel as DeiTModel, __webpack_exports__DeiTPreTrainedModel as DeiTPreTrainedModel, __webpack_exports__DepthAnythingForDepthEstimation as DepthAnythingForDepthEstimation, __webpack_exports__DepthAnythingPreTrainedModel as DepthAnythingPreTrainedModel, __webpack_exports__DepthEstimationPipeline as DepthEstimationPipeline, __webpack_exports__DepthProForDepthEstimation as DepthProForDepthEstimation, __webpack_exports__DepthProPreTrainedModel as DepthProPreTrainedModel, __webpack_exports__DetrFeatureExtractor as DetrFeatureExtractor, __webpack_exports__DetrForObjectDetection as DetrForObjectDetection, __webpack_exports__DetrForSegmentation as DetrForSegmentation, __webpack_exports__DetrImageProcessor as DetrImageProcessor, __webpack_exports__DetrModel as DetrModel, __webpack_exports__DetrObjectDetectionOutput as DetrObjectDetectionOutput, __webpack_exports__DetrPreTrainedModel as DetrPreTrainedModel, __webpack_exports__DetrSegmentationOutput as DetrSegmentationOutput, __webpack_exports__Dinov2ForImageClassification as Dinov2ForImageClassification, __webpack_exports__Dinov2Model as Dinov2Model, __webpack_exports__Dinov2PreTrainedModel as Dinov2PreTrainedModel, __webpack_exports__DistilBertForMaskedLM as DistilBertForMaskedLM, __webpack_exports__DistilBertForQuestionAnswering as DistilBertForQuestionAnswering, __webpack_exports__DistilBertForSequenceClassification as DistilBertForSequenceClassification, __webpack_exports__DistilBertForTokenClassification as DistilBertForTokenClassification, __webpack_exports__DistilBertModel as DistilBertModel, __webpack_exports__DistilBertPreTrainedModel as DistilBertPreTrainedModel, __webpack_exports__DistilBertTokenizer as DistilBertTokenizer, __webpack_exports__DocumentQuestionAnsweringPipeline as DocumentQuestionAnsweringPipeline, __webpack_exports__DonutFeatureExtractor as DonutFeatureExtractor, __webpack_exports__DonutImageProcessor as DonutImageProcessor, __webpack_exports__DonutSwinModel as DonutSwinModel, __webpack_exports__DonutSwinPreTrainedModel as DonutSwinPreTrainedModel, __webpack_exports__EfficientNetForImageClassification as EfficientNetForImageClassification, __webpack_exports__EfficientNetImageProcessor as EfficientNetImageProcessor, __webpack_exports__EfficientNetModel as EfficientNetModel, __webpack_exports__EfficientNetPreTrainedModel as EfficientNetPreTrainedModel, __webpack_exports__ElectraForMaskedLM as ElectraForMaskedLM, __webpack_exports__ElectraForQuestionAnswering as ElectraForQuestionAnswering, __webpack_exports__ElectraForSequenceClassification as ElectraForSequenceClassification, __webpack_exports__ElectraForTokenClassification as ElectraForTokenClassification, __webpack_exports__ElectraModel as ElectraModel, __webpack_exports__ElectraPreTrainedModel as ElectraPreTrainedModel, __webpack_exports__ElectraTokenizer as ElectraTokenizer, __webpack_exports__EosTokenCriteria as EosTokenCriteria, __webpack_exports__EsmForMaskedLM as EsmForMaskedLM, __webpack_exports__EsmForSequenceClassification as EsmForSequenceClassification, __webpack_exports__EsmForTokenClassification as EsmForTokenClassification, __webpack_exports__EsmModel as EsmModel, __webpack_exports__EsmPreTrainedModel as EsmPreTrainedModel, __webpack_exports__EsmTokenizer as EsmTokenizer, __webpack_exports__FFT as FFT, __webpack_exports__FalconForCausalLM as FalconForCausalLM, __webpack_exports__FalconModel as FalconModel, __webpack_exports__FalconPreTrainedModel as FalconPreTrainedModel, __webpack_exports__FalconTokenizer as FalconTokenizer, __webpack_exports__FastViTForImageClassification as FastViTForImageClassification, __webpack_exports__FastViTModel as FastViTModel, __webpack_exports__FastViTPreTrainedModel as FastViTPreTrainedModel, __webpack_exports__FeatureExtractionPipeline as FeatureExtractionPipeline, __webpack_exports__FeatureExtractor as FeatureExtractor, __webpack_exports__FillMaskPipeline as FillMaskPipeline, __webpack_exports__Florence2ForConditionalGeneration as Florence2ForConditionalGeneration, __webpack_exports__Florence2PreTrainedModel as Florence2PreTrainedModel, __webpack_exports__Florence2Processor as Florence2Processor, __webpack_exports__ForcedBOSTokenLogitsProcessor as ForcedBOSTokenLogitsProcessor, __webpack_exports__ForcedEOSTokenLogitsProcessor as ForcedEOSTokenLogitsProcessor, __webpack_exports__GLPNFeatureExtractor as GLPNFeatureExtractor, __webpack_exports__GLPNForDepthEstimation as GLPNForDepthEstimation, __webpack_exports__GLPNModel as GLPNModel, __webpack_exports__GLPNPreTrainedModel as GLPNPreTrainedModel, __webpack_exports__GPT2LMHeadModel as GPT2LMHeadModel, __webpack_exports__GPT2Model as GPT2Model, __webpack_exports__GPT2PreTrainedModel as GPT2PreTrainedModel, __webpack_exports__GPT2Tokenizer as GPT2Tokenizer, __webpack_exports__GPTBigCodeForCausalLM as GPTBigCodeForCausalLM, __webpack_exports__GPTBigCodeModel as GPTBigCodeModel, __webpack_exports__GPTBigCodePreTrainedModel as GPTBigCodePreTrainedModel, __webpack_exports__GPTJForCausalLM as GPTJForCausalLM, __webpack_exports__GPTJModel as GPTJModel, __webpack_exports__GPTJPreTrainedModel as GPTJPreTrainedModel, __webpack_exports__GPTNeoForCausalLM as GPTNeoForCausalLM, __webpack_exports__GPTNeoModel as GPTNeoModel, __webpack_exports__GPTNeoPreTrainedModel as GPTNeoPreTrainedModel, __webpack_exports__GPTNeoXForCausalLM as GPTNeoXForCausalLM, __webpack_exports__GPTNeoXModel as GPTNeoXModel, __webpack_exports__GPTNeoXPreTrainedModel as GPTNeoXPreTrainedModel, __webpack_exports__GPTNeoXTokenizer as GPTNeoXTokenizer, __webpack_exports__Gemma2ForCausalLM as Gemma2ForCausalLM, __webpack_exports__Gemma2Model as Gemma2Model, __webpack_exports__Gemma2PreTrainedModel as Gemma2PreTrainedModel, __webpack_exports__GemmaForCausalLM as GemmaForCausalLM, __webpack_exports__GemmaModel as GemmaModel, __webpack_exports__GemmaPreTrainedModel as GemmaPreTrainedModel, __webpack_exports__GemmaTokenizer as GemmaTokenizer, __webpack_exports__GraniteForCausalLM as GraniteForCausalLM, __webpack_exports__GraniteModel as GraniteModel, __webpack_exports__GranitePreTrainedModel as GranitePreTrainedModel, __webpack_exports__Grok1Tokenizer as Grok1Tokenizer, __webpack_exports__GroupViTModel as GroupViTModel, __webpack_exports__GroupViTPreTrainedModel as GroupViTPreTrainedModel, __webpack_exports__HerbertTokenizer as HerbertTokenizer, __webpack_exports__HieraForImageClassification as HieraForImageClassification, __webpack_exports__HieraModel as HieraModel, __webpack_exports__HieraPreTrainedModel as HieraPreTrainedModel, __webpack_exports__HubertForCTC as HubertForCTC, __webpack_exports__HubertForSequenceClassification as HubertForSequenceClassification, __webpack_exports__HubertModel as HubertModel, __webpack_exports__HubertPreTrainedModel as HubertPreTrainedModel, __webpack_exports__ImageClassificationPipeline as ImageClassificationPipeline, __webpack_exports__ImageFeatureExtractionPipeline as ImageFeatureExtractionPipeline, __webpack_exports__ImageFeatureExtractor as ImageFeatureExtractor, __webpack_exports__ImageMattingOutput as ImageMattingOutput, __webpack_exports__ImageProcessor as ImageProcessor, __webpack_exports__ImageSegmentationPipeline as ImageSegmentationPipeline, __webpack_exports__ImageToImagePipeline as ImageToImagePipeline, __webpack_exports__ImageToTextPipeline as ImageToTextPipeline, __webpack_exports__InterruptableStoppingCriteria as InterruptableStoppingCriteria, __webpack_exports__JAISLMHeadModel as JAISLMHeadModel, __webpack_exports__JAISModel as JAISModel, __webpack_exports__JAISPreTrainedModel as JAISPreTrainedModel, __webpack_exports__JinaCLIPImageProcessor as JinaCLIPImageProcessor, __webpack_exports__JinaCLIPModel as JinaCLIPModel, __webpack_exports__JinaCLIPPreTrainedModel as JinaCLIPPreTrainedModel, __webpack_exports__JinaCLIPProcessor as JinaCLIPProcessor, __webpack_exports__JinaCLIPTextModel as JinaCLIPTextModel, __webpack_exports__JinaCLIPVisionModel as JinaCLIPVisionModel, __webpack_exports__LlamaForCausalLM as LlamaForCausalLM, __webpack_exports__LlamaModel as LlamaModel, __webpack_exports__LlamaPreTrainedModel as LlamaPreTrainedModel, __webpack_exports__LlamaTokenizer as LlamaTokenizer, __webpack_exports__LlavaForConditionalGeneration as LlavaForConditionalGeneration, __webpack_exports__LlavaOnevisionForConditionalGeneration as LlavaOnevisionForConditionalGeneration, __webpack_exports__LlavaOnevisionImageProcessor as LlavaOnevisionImageProcessor, __webpack_exports__LlavaPreTrainedModel as LlavaPreTrainedModel, __webpack_exports__LogitsProcessor as LogitsProcessor, __webpack_exports__LogitsProcessorList as LogitsProcessorList, __webpack_exports__LogitsWarper as LogitsWarper, __webpack_exports__LongT5ForConditionalGeneration as LongT5ForConditionalGeneration, __webpack_exports__LongT5Model as LongT5Model, __webpack_exports__LongT5PreTrainedModel as LongT5PreTrainedModel, __webpack_exports__M2M100ForConditionalGeneration as M2M100ForConditionalGeneration, __webpack_exports__M2M100Model as M2M100Model, __webpack_exports__M2M100PreTrainedModel as M2M100PreTrainedModel, __webpack_exports__M2M100Tokenizer as M2M100Tokenizer, __webpack_exports__MBart50Tokenizer as MBart50Tokenizer, __webpack_exports__MBartForCausalLM as MBartForCausalLM, __webpack_exports__MBartForConditionalGeneration as MBartForConditionalGeneration, __webpack_exports__MBartForSequenceClassification as MBartForSequenceClassification, __webpack_exports__MBartModel as MBartModel, __webpack_exports__MBartPreTrainedModel as MBartPreTrainedModel, __webpack_exports__MBartTokenizer as MBartTokenizer, __webpack_exports__MPNetForMaskedLM as MPNetForMaskedLM, __webpack_exports__MPNetForQuestionAnswering as MPNetForQuestionAnswering, __webpack_exports__MPNetForSequenceClassification as MPNetForSequenceClassification, __webpack_exports__MPNetForTokenClassification as MPNetForTokenClassification, __webpack_exports__MPNetModel as MPNetModel, __webpack_exports__MPNetPreTrainedModel as MPNetPreTrainedModel, __webpack_exports__MPNetTokenizer as MPNetTokenizer, __webpack_exports__MT5ForConditionalGeneration as MT5ForConditionalGeneration, __webpack_exports__MT5Model as MT5Model, __webpack_exports__MT5PreTrainedModel as MT5PreTrainedModel, __webpack_exports__MarianMTModel as MarianMTModel, __webpack_exports__MarianModel as MarianModel, __webpack_exports__MarianPreTrainedModel as MarianPreTrainedModel, __webpack_exports__MarianTokenizer as MarianTokenizer, __webpack_exports__Mask2FormerImageProcessor as Mask2FormerImageProcessor, __webpack_exports__MaskFormerFeatureExtractor as MaskFormerFeatureExtractor, __webpack_exports__MaskFormerForInstanceSegmentation as MaskFormerForInstanceSegmentation, __webpack_exports__MaskFormerImageProcessor as MaskFormerImageProcessor, __webpack_exports__MaskFormerModel as MaskFormerModel, __webpack_exports__MaskFormerPreTrainedModel as MaskFormerPreTrainedModel, __webpack_exports__MaskedLMOutput as MaskedLMOutput, __webpack_exports__MaxLengthCriteria as MaxLengthCriteria, __webpack_exports__MgpstrForSceneTextRecognition as MgpstrForSceneTextRecognition, __webpack_exports__MgpstrModelOutput as MgpstrModelOutput, __webpack_exports__MgpstrPreTrainedModel as MgpstrPreTrainedModel, __webpack_exports__MgpstrProcessor as MgpstrProcessor, __webpack_exports__MgpstrTokenizer as MgpstrTokenizer, __webpack_exports__MinLengthLogitsProcessor as MinLengthLogitsProcessor, __webpack_exports__MinNewTokensLengthLogitsProcessor as MinNewTokensLengthLogitsProcessor, __webpack_exports__MistralForCausalLM as MistralForCausalLM, __webpack_exports__MistralModel as MistralModel, __webpack_exports__MistralPreTrainedModel as MistralPreTrainedModel, __webpack_exports__MobileBertForMaskedLM as MobileBertForMaskedLM, __webpack_exports__MobileBertForQuestionAnswering as MobileBertForQuestionAnswering, __webpack_exports__MobileBertForSequenceClassification as MobileBertForSequenceClassification, __webpack_exports__MobileBertModel as MobileBertModel, __webpack_exports__MobileBertPreTrainedModel as MobileBertPreTrainedModel, __webpack_exports__MobileBertTokenizer as MobileBertTokenizer, __webpack_exports__MobileLLMForCausalLM as MobileLLMForCausalLM, __webpack_exports__MobileLLMModel as MobileLLMModel, __webpack_exports__MobileLLMPreTrainedModel as MobileLLMPreTrainedModel, __webpack_exports__MobileNetV1FeatureExtractor as MobileNetV1FeatureExtractor, __webpack_exports__MobileNetV1ForImageClassification as MobileNetV1ForImageClassification, __webpack_exports__MobileNetV1ImageProcessor as MobileNetV1ImageProcessor, __webpack_exports__MobileNetV1Model as MobileNetV1Model, __webpack_exports__MobileNetV1PreTrainedModel as MobileNetV1PreTrainedModel, __webpack_exports__MobileNetV2FeatureExtractor as MobileNetV2FeatureExtractor, __webpack_exports__MobileNetV2ForImageClassification as MobileNetV2ForImageClassification, __webpack_exports__MobileNetV2ImageProcessor as MobileNetV2ImageProcessor, __webpack_exports__MobileNetV2Model as MobileNetV2Model, __webpack_exports__MobileNetV2PreTrainedModel as MobileNetV2PreTrainedModel, __webpack_exports__MobileNetV3FeatureExtractor as MobileNetV3FeatureExtractor, __webpack_exports__MobileNetV3ForImageClassification as MobileNetV3ForImageClassification, __webpack_exports__MobileNetV3ImageProcessor as MobileNetV3ImageProcessor, __webpack_exports__MobileNetV3Model as MobileNetV3Model, __webpack_exports__MobileNetV3PreTrainedModel as MobileNetV3PreTrainedModel, __webpack_exports__MobileNetV4FeatureExtractor as MobileNetV4FeatureExtractor, __webpack_exports__MobileNetV4ForImageClassification as MobileNetV4ForImageClassification, __webpack_exports__MobileNetV4ImageProcessor as MobileNetV4ImageProcessor, __webpack_exports__MobileNetV4Model as MobileNetV4Model, __webpack_exports__MobileNetV4PreTrainedModel as MobileNetV4PreTrainedModel, __webpack_exports__MobileViTFeatureExtractor as MobileViTFeatureExtractor, __webpack_exports__MobileViTForImageClassification as MobileViTForImageClassification, __webpack_exports__MobileViTImageProcessor as MobileViTImageProcessor, __webpack_exports__MobileViTModel as MobileViTModel, __webpack_exports__MobileViTPreTrainedModel as MobileViTPreTrainedModel, __webpack_exports__MobileViTV2ForImageClassification as MobileViTV2ForImageClassification, __webpack_exports__MobileViTV2Model as MobileViTV2Model, __webpack_exports__MobileViTV2PreTrainedModel as MobileViTV2PreTrainedModel, __webpack_exports__ModelOutput as ModelOutput, __webpack_exports__Moondream1ForConditionalGeneration as Moondream1ForConditionalGeneration, __webpack_exports__MptForCausalLM as MptForCausalLM, __webpack_exports__MptModel as MptModel, __webpack_exports__MptPreTrainedModel as MptPreTrainedModel, __webpack_exports__MultiModalityCausalLM as MultiModalityCausalLM, __webpack_exports__MultiModalityPreTrainedModel as MultiModalityPreTrainedModel, __webpack_exports__MusicgenForCausalLM as MusicgenForCausalLM, __webpack_exports__MusicgenForConditionalGeneration as MusicgenForConditionalGeneration, __webpack_exports__MusicgenModel as MusicgenModel, __webpack_exports__MusicgenPreTrainedModel as MusicgenPreTrainedModel, __webpack_exports__NllbTokenizer as NllbTokenizer, __webpack_exports__NoBadWordsLogitsProcessor as NoBadWordsLogitsProcessor, __webpack_exports__NoRepeatNGramLogitsProcessor as NoRepeatNGramLogitsProcessor, __webpack_exports__NomicBertModel as NomicBertModel, __webpack_exports__NomicBertPreTrainedModel as NomicBertPreTrainedModel, __webpack_exports__NougatImageProcessor as NougatImageProcessor, __webpack_exports__NougatTokenizer as NougatTokenizer, __webpack_exports__OPTForCausalLM as OPTForCausalLM, __webpack_exports__OPTModel as OPTModel, __webpack_exports__OPTPreTrainedModel as OPTPreTrainedModel, __webpack_exports__ObjectDetectionPipeline as ObjectDetectionPipeline, __webpack_exports__OlmoForCausalLM as OlmoForCausalLM, __webpack_exports__OlmoModel as OlmoModel, __webpack_exports__OlmoPreTrainedModel as OlmoPreTrainedModel, __webpack_exports__OpenELMForCausalLM as OpenELMForCausalLM, __webpack_exports__OpenELMModel as OpenELMModel, __webpack_exports__OpenELMPreTrainedModel as OpenELMPreTrainedModel, __webpack_exports__OwlViTFeatureExtractor as OwlViTFeatureExtractor, __webpack_exports__OwlViTForObjectDetection as OwlViTForObjectDetection, __webpack_exports__OwlViTImageProcessor as OwlViTImageProcessor, __webpack_exports__OwlViTModel as OwlViTModel, __webpack_exports__OwlViTPreTrainedModel as OwlViTPreTrainedModel, __webpack_exports__OwlViTProcessor as OwlViTProcessor, __webpack_exports__Owlv2ForObjectDetection as Owlv2ForObjectDetection, __webpack_exports__Owlv2ImageProcessor as Owlv2ImageProcessor, __webpack_exports__Owlv2Model as Owlv2Model, __webpack_exports__Owlv2PreTrainedModel as Owlv2PreTrainedModel, __webpack_exports__PatchTSMixerForPrediction as PatchTSMixerForPrediction, __webpack_exports__PatchTSMixerModel as PatchTSMixerModel, __webpack_exports__PatchTSMixerPreTrainedModel as PatchTSMixerPreTrainedModel, __webpack_exports__PatchTSTForPrediction as PatchTSTForPrediction, __webpack_exports__PatchTSTModel as PatchTSTModel, __webpack_exports__PatchTSTPreTrainedModel as PatchTSTPreTrainedModel, __webpack_exports__Phi3ForCausalLM as Phi3ForCausalLM, __webpack_exports__Phi3Model as Phi3Model, __webpack_exports__Phi3PreTrainedModel as Phi3PreTrainedModel, __webpack_exports__PhiForCausalLM as PhiForCausalLM, __webpack_exports__PhiModel as PhiModel, __webpack_exports__PhiPreTrainedModel as PhiPreTrainedModel, __webpack_exports__Pipeline as Pipeline, __webpack_exports__PreTrainedModel as PreTrainedModel, __webpack_exports__PreTrainedTokenizer as PreTrainedTokenizer, __webpack_exports__PretrainedConfig as PretrainedConfig, __webpack_exports__PretrainedMixin as PretrainedMixin, __webpack_exports__Processor as Processor, __webpack_exports__PvtForImageClassification as PvtForImageClassification, __webpack_exports__PvtImageProcessor as PvtImageProcessor, __webpack_exports__PvtModel as PvtModel, __webpack_exports__PvtPreTrainedModel as PvtPreTrainedModel, __webpack_exports__PyAnnoteFeatureExtractor as PyAnnoteFeatureExtractor, __webpack_exports__PyAnnoteForAudioFrameClassification as PyAnnoteForAudioFrameClassification, __webpack_exports__PyAnnoteModel as PyAnnoteModel, __webpack_exports__PyAnnotePreTrainedModel as PyAnnotePreTrainedModel, __webpack_exports__PyAnnoteProcessor as PyAnnoteProcessor, __webpack_exports__QuestionAnsweringModelOutput as QuestionAnsweringModelOutput, __webpack_exports__QuestionAnsweringPipeline as QuestionAnsweringPipeline, __webpack_exports__Qwen2ForCausalLM as Qwen2ForCausalLM, __webpack_exports__Qwen2Model as Qwen2Model, __webpack_exports__Qwen2PreTrainedModel as Qwen2PreTrainedModel, __webpack_exports__Qwen2Tokenizer as Qwen2Tokenizer, __webpack_exports__Qwen2VLForConditionalGeneration as Qwen2VLForConditionalGeneration, __webpack_exports__Qwen2VLImageProcessor as Qwen2VLImageProcessor, __webpack_exports__Qwen2VLPreTrainedModel as Qwen2VLPreTrainedModel, __webpack_exports__Qwen2VLProcessor as Qwen2VLProcessor, __webpack_exports__RTDetrForObjectDetection as RTDetrForObjectDetection, __webpack_exports__RTDetrImageProcessor as RTDetrImageProcessor, __webpack_exports__RTDetrModel as RTDetrModel, __webpack_exports__RTDetrObjectDetectionOutput as RTDetrObjectDetectionOutput, __webpack_exports__RTDetrPreTrainedModel as RTDetrPreTrainedModel, __webpack_exports__RawImage as RawImage, __webpack_exports__RepetitionPenaltyLogitsProcessor as RepetitionPenaltyLogitsProcessor, __webpack_exports__ResNetForImageClassification as ResNetForImageClassification, __webpack_exports__ResNetModel as ResNetModel, __webpack_exports__ResNetPreTrainedModel as ResNetPreTrainedModel, __webpack_exports__RoFormerForMaskedLM as RoFormerForMaskedLM, __webpack_exports__RoFormerForQuestionAnswering as RoFormerForQuestionAnswering, __webpack_exports__RoFormerForSequenceClassification as RoFormerForSequenceClassification, __webpack_exports__RoFormerForTokenClassification as RoFormerForTokenClassification, __webpack_exports__RoFormerModel as RoFormerModel, __webpack_exports__RoFormerPreTrainedModel as RoFormerPreTrainedModel, __webpack_exports__RoFormerTokenizer as RoFormerTokenizer, __webpack_exports__RobertaForMaskedLM as RobertaForMaskedLM, __webpack_exports__RobertaForQuestionAnswering as RobertaForQuestionAnswering, __webpack_exports__RobertaForSequenceClassification as RobertaForSequenceClassification, __webpack_exports__RobertaForTokenClassification as RobertaForTokenClassification, __webpack_exports__RobertaModel as RobertaModel, __webpack_exports__RobertaPreTrainedModel as RobertaPreTrainedModel, __webpack_exports__RobertaTokenizer as RobertaTokenizer, __webpack_exports__SamImageProcessor as SamImageProcessor, __webpack_exports__SamImageSegmentationOutput as SamImageSegmentationOutput, __webpack_exports__SamModel as SamModel, __webpack_exports__SamPreTrainedModel as SamPreTrainedModel, __webpack_exports__SamProcessor as SamProcessor, __webpack_exports__SapiensForDepthEstimation as SapiensForDepthEstimation, __webpack_exports__SapiensForNormalEstimation as SapiensForNormalEstimation, __webpack_exports__SapiensForSemanticSegmentation as SapiensForSemanticSegmentation, __webpack_exports__SapiensPreTrainedModel as SapiensPreTrainedModel, __webpack_exports__SeamlessM4TFeatureExtractor as SeamlessM4TFeatureExtractor, __webpack_exports__SegformerFeatureExtractor as SegformerFeatureExtractor, __webpack_exports__SegformerForImageClassification as SegformerForImageClassification, __webpack_exports__SegformerForSemanticSegmentation as SegformerForSemanticSegmentation, __webpack_exports__SegformerImageProcessor as SegformerImageProcessor, __webpack_exports__SegformerModel as SegformerModel, __webpack_exports__SegformerPreTrainedModel as SegformerPreTrainedModel, __webpack_exports__Seq2SeqLMOutput as Seq2SeqLMOutput, __webpack_exports__SequenceClassifierOutput as SequenceClassifierOutput, __webpack_exports__SiglipImageProcessor as SiglipImageProcessor, __webpack_exports__SiglipModel as SiglipModel, __webpack_exports__SiglipPreTrainedModel as SiglipPreTrainedModel, __webpack_exports__SiglipTextModel as SiglipTextModel, __webpack_exports__SiglipTokenizer as SiglipTokenizer, __webpack_exports__SiglipVisionModel as SiglipVisionModel, __webpack_exports__SpeechT5FeatureExtractor as SpeechT5FeatureExtractor, __webpack_exports__SpeechT5ForSpeechToText as SpeechT5ForSpeechToText, __webpack_exports__SpeechT5ForTextToSpeech as SpeechT5ForTextToSpeech, __webpack_exports__SpeechT5HifiGan as SpeechT5HifiGan, __webpack_exports__SpeechT5Model as SpeechT5Model, __webpack_exports__SpeechT5PreTrainedModel as SpeechT5PreTrainedModel, __webpack_exports__SpeechT5Processor as SpeechT5Processor, __webpack_exports__SpeechT5Tokenizer as SpeechT5Tokenizer, __webpack_exports__SqueezeBertForMaskedLM as SqueezeBertForMaskedLM, __webpack_exports__SqueezeBertForQuestionAnswering as SqueezeBertForQuestionAnswering, __webpack_exports__SqueezeBertForSequenceClassification as SqueezeBertForSequenceClassification, __webpack_exports__SqueezeBertModel as SqueezeBertModel, __webpack_exports__SqueezeBertPreTrainedModel as SqueezeBertPreTrainedModel, __webpack_exports__SqueezeBertTokenizer as SqueezeBertTokenizer, __webpack_exports__StableLmForCausalLM as StableLmForCausalLM, __webpack_exports__StableLmModel as StableLmModel, __webpack_exports__StableLmPreTrainedModel as StableLmPreTrainedModel, __webpack_exports__Starcoder2ForCausalLM as Starcoder2ForCausalLM, __webpack_exports__Starcoder2Model as Starcoder2Model, __webpack_exports__Starcoder2PreTrainedModel as Starcoder2PreTrainedModel, __webpack_exports__StoppingCriteria as StoppingCriteria, __webpack_exports__StoppingCriteriaList as StoppingCriteriaList, __webpack_exports__SummarizationPipeline as SummarizationPipeline, __webpack_exports__SuppressTokensAtBeginLogitsProcessor as SuppressTokensAtBeginLogitsProcessor, __webpack_exports__Swin2SRForImageSuperResolution as Swin2SRForImageSuperResolution, __webpack_exports__Swin2SRImageProcessor as Swin2SRImageProcessor, __webpack_exports__Swin2SRModel as Swin2SRModel, __webpack_exports__Swin2SRPreTrainedModel as Swin2SRPreTrainedModel, __webpack_exports__SwinForImageClassification as SwinForImageClassification, __webpack_exports__SwinModel as SwinModel, __webpack_exports__SwinPreTrainedModel as SwinPreTrainedModel, __webpack_exports__T5ForConditionalGeneration as T5ForConditionalGeneration, __webpack_exports__T5Model as T5Model, __webpack_exports__T5PreTrainedModel as T5PreTrainedModel, __webpack_exports__T5Tokenizer as T5Tokenizer, __webpack_exports__TableTransformerForObjectDetection as TableTransformerForObjectDetection, __webpack_exports__TableTransformerModel as TableTransformerModel, __webpack_exports__TableTransformerObjectDetectionOutput as TableTransformerObjectDetectionOutput, __webpack_exports__TableTransformerPreTrainedModel as TableTransformerPreTrainedModel, __webpack_exports__TemperatureLogitsWarper as TemperatureLogitsWarper, __webpack_exports__Tensor as Tensor, __webpack_exports__Text2TextGenerationPipeline as Text2TextGenerationPipeline, __webpack_exports__TextClassificationPipeline as TextClassificationPipeline, __webpack_exports__TextGenerationPipeline as TextGenerationPipeline, __webpack_exports__TextStreamer as TextStreamer, __webpack_exports__TextToAudioPipeline as TextToAudioPipeline, __webpack_exports__TokenClassificationPipeline as TokenClassificationPipeline, __webpack_exports__TokenClassifierOutput as TokenClassifierOutput, __webpack_exports__TokenizerModel as TokenizerModel, __webpack_exports__TopKLogitsWarper as TopKLogitsWarper, __webpack_exports__TopPLogitsWarper as TopPLogitsWarper, __webpack_exports__TrOCRForCausalLM as TrOCRForCausalLM, __webpack_exports__TrOCRPreTrainedModel as TrOCRPreTrainedModel, __webpack_exports__TranslationPipeline as TranslationPipeline, __webpack_exports__UniSpeechForCTC as UniSpeechForCTC, __webpack_exports__UniSpeechForSequenceClassification as UniSpeechForSequenceClassification, __webpack_exports__UniSpeechModel as UniSpeechModel, __webpack_exports__UniSpeechPreTrainedModel as UniSpeechPreTrainedModel, __webpack_exports__UniSpeechSatForAudioFrameClassification as UniSpeechSatForAudioFrameClassification, __webpack_exports__UniSpeechSatForCTC as UniSpeechSatForCTC, __webpack_exports__UniSpeechSatForSequenceClassification as UniSpeechSatForSequenceClassification, __webpack_exports__UniSpeechSatModel as UniSpeechSatModel, __webpack_exports__UniSpeechSatPreTrainedModel as UniSpeechSatPreTrainedModel, __webpack_exports__VLChatProcessor as VLChatProcessor, __webpack_exports__VLMImageProcessor as VLMImageProcessor, __webpack_exports__ViTFeatureExtractor as ViTFeatureExtractor, __webpack_exports__ViTForImageClassification as ViTForImageClassification, __webpack_exports__ViTImageProcessor as ViTImageProcessor, __webpack_exports__ViTMAEModel as ViTMAEModel, __webpack_exports__ViTMAEPreTrainedModel as ViTMAEPreTrainedModel, __webpack_exports__ViTMSNForImageClassification as ViTMSNForImageClassification, __webpack_exports__ViTMSNModel as ViTMSNModel, __webpack_exports__ViTMSNPreTrainedModel as ViTMSNPreTrainedModel, __webpack_exports__ViTModel as ViTModel, __webpack_exports__ViTPreTrainedModel as ViTPreTrainedModel, __webpack_exports__VisionEncoderDecoderModel as VisionEncoderDecoderModel, __webpack_exports__VitMatteForImageMatting as VitMatteForImageMatting, __webpack_exports__VitMatteImageProcessor as VitMatteImageProcessor, __webpack_exports__VitMattePreTrainedModel as VitMattePreTrainedModel, __webpack_exports__VitPoseForPoseEstimation as VitPoseForPoseEstimation, __webpack_exports__VitPoseImageProcessor as VitPoseImageProcessor, __webpack_exports__VitPosePreTrainedModel as VitPosePreTrainedModel, __webpack_exports__VitsModel as VitsModel, __webpack_exports__VitsModelOutput as VitsModelOutput, __webpack_exports__VitsPreTrainedModel as VitsPreTrainedModel, __webpack_exports__VitsTokenizer as VitsTokenizer, __webpack_exports__Wav2Vec2BertForCTC as Wav2Vec2BertForCTC, __webpack_exports__Wav2Vec2BertForSequenceClassification as Wav2Vec2BertForSequenceClassification, __webpack_exports__Wav2Vec2BertModel as Wav2Vec2BertModel, __webpack_exports__Wav2Vec2BertPreTrainedModel as Wav2Vec2BertPreTrainedModel, __webpack_exports__Wav2Vec2CTCTokenizer as Wav2Vec2CTCTokenizer, __webpack_exports__Wav2Vec2FeatureExtractor as Wav2Vec2FeatureExtractor, __webpack_exports__Wav2Vec2ForAudioFrameClassification as Wav2Vec2ForAudioFrameClassification, __webpack_exports__Wav2Vec2ForCTC as Wav2Vec2ForCTC, __webpack_exports__Wav2Vec2ForSequenceClassification as Wav2Vec2ForSequenceClassification, __webpack_exports__Wav2Vec2Model as Wav2Vec2Model, __webpack_exports__Wav2Vec2PreTrainedModel as Wav2Vec2PreTrainedModel, __webpack_exports__Wav2Vec2ProcessorWithLM as Wav2Vec2ProcessorWithLM, __webpack_exports__WavLMForAudioFrameClassification as WavLMForAudioFrameClassification, __webpack_exports__WavLMForCTC as WavLMForCTC, __webpack_exports__WavLMForSequenceClassification as WavLMForSequenceClassification, __webpack_exports__WavLMForXVector as WavLMForXVector, __webpack_exports__WavLMModel as WavLMModel, __webpack_exports__WavLMPreTrainedModel as WavLMPreTrainedModel, __webpack_exports__WeSpeakerFeatureExtractor as WeSpeakerFeatureExtractor, __webpack_exports__WeSpeakerResNetModel as WeSpeakerResNetModel, __webpack_exports__WeSpeakerResNetPreTrainedModel as WeSpeakerResNetPreTrainedModel, __webpack_exports__WhisperFeatureExtractor as WhisperFeatureExtractor, __webpack_exports__WhisperForConditionalGeneration as WhisperForConditionalGeneration, __webpack_exports__WhisperModel as WhisperModel, __webpack_exports__WhisperPreTrainedModel as WhisperPreTrainedModel, __webpack_exports__WhisperProcessor as WhisperProcessor, __webpack_exports__WhisperTextStreamer as WhisperTextStreamer, __webpack_exports__WhisperTimeStampLogitsProcessor as WhisperTimeStampLogitsProcessor, __webpack_exports__WhisperTokenizer as WhisperTokenizer, __webpack_exports__XLMForQuestionAnswering as XLMForQuestionAnswering, __webpack_exports__XLMForSequenceClassification as XLMForSequenceClassification, __webpack_exports__XLMForTokenClassification as XLMForTokenClassification, __webpack_exports__XLMModel as XLMModel, __webpack_exports__XLMPreTrainedModel as XLMPreTrainedModel, __webpack_exports__XLMRobertaForMaskedLM as XLMRobertaForMaskedLM, __webpack_exports__XLMRobertaForQuestionAnswering as XLMRobertaForQuestionAnswering, __webpack_exports__XLMRobertaForSequenceClassification as XLMRobertaForSequenceClassification, __webpack_exports__XLMRobertaForTokenClassification as XLMRobertaForTokenClassification, __webpack_exports__XLMRobertaModel as XLMRobertaModel, __webpack_exports__XLMRobertaPreTrainedModel as XLMRobertaPreTrainedModel, __webpack_exports__XLMRobertaTokenizer as XLMRobertaTokenizer, __webpack_exports__XLMTokenizer as XLMTokenizer, __webpack_exports__XLMWithLMHeadModel as XLMWithLMHeadModel, __webpack_exports__XVectorOutput as XVectorOutput, __webpack_exports__YolosFeatureExtractor as YolosFeatureExtractor, __webpack_exports__YolosForObjectDetection as YolosForObjectDetection, __webpack_exports__YolosImageProcessor as YolosImageProcessor, __webpack_exports__YolosModel as YolosModel, __webpack_exports__YolosObjectDetectionOutput as YolosObjectDetectionOutput, __webpack_exports__YolosPreTrainedModel as YolosPreTrainedModel, __webpack_exports__ZeroShotAudioClassificationPipeline as ZeroShotAudioClassificationPipeline, __webpack_exports__ZeroShotClassificationPipeline as ZeroShotClassificationPipeline, __webpack_exports__ZeroShotImageClassificationPipeline as ZeroShotImageClassificationPipeline, __webpack_exports__ZeroShotObjectDetectionPipeline as ZeroShotObjectDetectionPipeline, __webpack_exports__bankers_round as bankers_round, __webpack_exports__cat as cat, __webpack_exports__cos_sim as cos_sim, __webpack_exports__dot as dot, __webpack_exports__dynamic_time_warping as dynamic_time_warping, __webpack_exports__env as env, __webpack_exports__full as full, __webpack_exports__full_like as full_like, __webpack_exports__getKeyValueShapes as getKeyValueShapes, __webpack_exports__hamming as hamming, __webpack_exports__hanning as hanning, __webpack_exports__interpolate as interpolate, __webpack_exports__interpolate_4d as interpolate_4d, __webpack_exports__interpolate_data as interpolate_data, __webpack_exports__is_chinese_char as is_chinese_char, __webpack_exports__layer_norm as layer_norm, __webpack_exports__log_softmax as log_softmax, __webpack_exports__magnitude as magnitude, __webpack_exports__matmul as matmul, __webpack_exports__max as max, __webpack_exports__mean as mean, __webpack_exports__mean_pooling as mean_pooling, __webpack_exports__medianFilter as medianFilter, __webpack_exports__mel_filter_bank as mel_filter_bank, __webpack_exports__min as min, __webpack_exports__ones as ones, __webpack_exports__ones_like as ones_like, __webpack_exports__permute as permute, __webpack_exports__permute_data as permute_data, __webpack_exports__pipeline as pipeline, __webpack_exports__quantize_embeddings as quantize_embeddings, __webpack_exports__read_audio as read_audio, __webpack_exports__rfft as rfft, __webpack_exports__round as round, __webpack_exports__softmax as softmax, __webpack_exports__spectrogram as spectrogram, __webpack_exports__stack as stack, __webpack_exports__std_mean as std_mean, __webpack_exports__topk as topk, __webpack_exports__window_function as window_function, __webpack_exports__zeros as zeros, __webpack_exports__zeros_like as zeros_like };
+export { __webpack_exports__ASTFeatureExtractor as ASTFeatureExtractor, __webpack_exports__ASTForAudioClassification as ASTForAudioClassification, __webpack_exports__ASTModel as ASTModel, __webpack_exports__ASTPreTrainedModel as ASTPreTrainedModel, __webpack_exports__AlbertForMaskedLM as AlbertForMaskedLM, __webpack_exports__AlbertForQuestionAnswering as AlbertForQuestionAnswering, __webpack_exports__AlbertForSequenceClassification as AlbertForSequenceClassification, __webpack_exports__AlbertModel as AlbertModel, __webpack_exports__AlbertPreTrainedModel as AlbertPreTrainedModel, __webpack_exports__AlbertTokenizer as AlbertTokenizer, __webpack_exports__AudioClassificationPipeline as AudioClassificationPipeline, __webpack_exports__AutoConfig as AutoConfig, __webpack_exports__AutoFeatureExtractor as AutoFeatureExtractor, __webpack_exports__AutoImageProcessor as AutoImageProcessor, __webpack_exports__AutoModel as AutoModel, __webpack_exports__AutoModelForAudioClassification as AutoModelForAudioClassification, __webpack_exports__AutoModelForAudioFrameClassification as AutoModelForAudioFrameClassification, __webpack_exports__AutoModelForCTC as AutoModelForCTC, __webpack_exports__AutoModelForCausalLM as AutoModelForCausalLM, __webpack_exports__AutoModelForDepthEstimation as AutoModelForDepthEstimation, __webpack_exports__AutoModelForDocumentQuestionAnswering as AutoModelForDocumentQuestionAnswering, __webpack_exports__AutoModelForImageClassification as AutoModelForImageClassification, __webpack_exports__AutoModelForImageFeatureExtraction as AutoModelForImageFeatureExtraction, __webpack_exports__AutoModelForImageMatting as AutoModelForImageMatting, __webpack_exports__AutoModelForImageSegmentation as AutoModelForImageSegmentation, __webpack_exports__AutoModelForImageToImage as AutoModelForImageToImage, __webpack_exports__AutoModelForMaskGeneration as AutoModelForMaskGeneration, __webpack_exports__AutoModelForMaskedLM as AutoModelForMaskedLM, __webpack_exports__AutoModelForNormalEstimation as AutoModelForNormalEstimation, __webpack_exports__AutoModelForObjectDetection as AutoModelForObjectDetection, __webpack_exports__AutoModelForPoseEstimation as AutoModelForPoseEstimation, __webpack_exports__AutoModelForQuestionAnswering as AutoModelForQuestionAnswering, __webpack_exports__AutoModelForSemanticSegmentation as AutoModelForSemanticSegmentation, __webpack_exports__AutoModelForSeq2SeqLM as AutoModelForSeq2SeqLM, __webpack_exports__AutoModelForSequenceClassification as AutoModelForSequenceClassification, __webpack_exports__AutoModelForSpeechSeq2Seq as AutoModelForSpeechSeq2Seq, __webpack_exports__AutoModelForTextToSpectrogram as AutoModelForTextToSpectrogram, __webpack_exports__AutoModelForTextToWaveform as AutoModelForTextToWaveform, __webpack_exports__AutoModelForTokenClassification as AutoModelForTokenClassification, __webpack_exports__AutoModelForUniversalSegmentation as AutoModelForUniversalSegmentation, __webpack_exports__AutoModelForVision2Seq as AutoModelForVision2Seq, __webpack_exports__AutoModelForXVector as AutoModelForXVector, __webpack_exports__AutoModelForZeroShotObjectDetection as AutoModelForZeroShotObjectDetection, __webpack_exports__AutoProcessor as AutoProcessor, __webpack_exports__AutoTokenizer as AutoTokenizer, __webpack_exports__AutomaticSpeechRecognitionPipeline as AutomaticSpeechRecognitionPipeline, __webpack_exports__BartForConditionalGeneration as BartForConditionalGeneration, __webpack_exports__BartForSequenceClassification as BartForSequenceClassification, __webpack_exports__BartModel as BartModel, __webpack_exports__BartPretrainedModel as BartPretrainedModel, __webpack_exports__BartTokenizer as BartTokenizer, __webpack_exports__BaseModelOutput as BaseModelOutput, __webpack_exports__BaseStreamer as BaseStreamer, __webpack_exports__BeitFeatureExtractor as BeitFeatureExtractor, __webpack_exports__BeitForImageClassification as BeitForImageClassification, __webpack_exports__BeitModel as BeitModel, __webpack_exports__BeitPreTrainedModel as BeitPreTrainedModel, __webpack_exports__BertForMaskedLM as BertForMaskedLM, __webpack_exports__BertForQuestionAnswering as BertForQuestionAnswering, __webpack_exports__BertForSequenceClassification as BertForSequenceClassification, __webpack_exports__BertForTokenClassification as BertForTokenClassification, __webpack_exports__BertModel as BertModel, __webpack_exports__BertPreTrainedModel as BertPreTrainedModel, __webpack_exports__BertTokenizer as BertTokenizer, __webpack_exports__BitImageProcessor as BitImageProcessor, __webpack_exports__BlenderbotForConditionalGeneration as BlenderbotForConditionalGeneration, __webpack_exports__BlenderbotModel as BlenderbotModel, __webpack_exports__BlenderbotPreTrainedModel as BlenderbotPreTrainedModel, __webpack_exports__BlenderbotSmallForConditionalGeneration as BlenderbotSmallForConditionalGeneration, __webpack_exports__BlenderbotSmallModel as BlenderbotSmallModel, __webpack_exports__BlenderbotSmallPreTrainedModel as BlenderbotSmallPreTrainedModel, __webpack_exports__BlenderbotSmallTokenizer as BlenderbotSmallTokenizer, __webpack_exports__BlenderbotTokenizer as BlenderbotTokenizer, __webpack_exports__BloomForCausalLM as BloomForCausalLM, __webpack_exports__BloomModel as BloomModel, __webpack_exports__BloomPreTrainedModel as BloomPreTrainedModel, __webpack_exports__BloomTokenizer as BloomTokenizer, __webpack_exports__CLIPFeatureExtractor as CLIPFeatureExtractor, __webpack_exports__CLIPImageProcessor as CLIPImageProcessor, __webpack_exports__CLIPModel as CLIPModel, __webpack_exports__CLIPPreTrainedModel as CLIPPreTrainedModel, __webpack_exports__CLIPSegForImageSegmentation as CLIPSegForImageSegmentation, __webpack_exports__CLIPSegModel as CLIPSegModel, __webpack_exports__CLIPSegPreTrainedModel as CLIPSegPreTrainedModel, __webpack_exports__CLIPTextModel as CLIPTextModel, __webpack_exports__CLIPTextModelWithProjection as CLIPTextModelWithProjection, __webpack_exports__CLIPTokenizer as CLIPTokenizer, __webpack_exports__CLIPVisionModel as CLIPVisionModel, __webpack_exports__CLIPVisionModelWithProjection as CLIPVisionModelWithProjection, __webpack_exports__CamembertForMaskedLM as CamembertForMaskedLM, __webpack_exports__CamembertForQuestionAnswering as CamembertForQuestionAnswering, __webpack_exports__CamembertForSequenceClassification as CamembertForSequenceClassification, __webpack_exports__CamembertForTokenClassification as CamembertForTokenClassification, __webpack_exports__CamembertModel as CamembertModel, __webpack_exports__CamembertPreTrainedModel as CamembertPreTrainedModel, __webpack_exports__CamembertTokenizer as CamembertTokenizer, __webpack_exports__CausalLMOutput as CausalLMOutput, __webpack_exports__CausalLMOutputWithPast as CausalLMOutputWithPast, __webpack_exports__ChineseCLIPFeatureExtractor as ChineseCLIPFeatureExtractor, __webpack_exports__ChineseCLIPModel as ChineseCLIPModel, __webpack_exports__ChineseCLIPPreTrainedModel as ChineseCLIPPreTrainedModel, __webpack_exports__ClapAudioModelWithProjection as ClapAudioModelWithProjection, __webpack_exports__ClapFeatureExtractor as ClapFeatureExtractor, __webpack_exports__ClapModel as ClapModel, __webpack_exports__ClapPreTrainedModel as ClapPreTrainedModel, __webpack_exports__ClapTextModelWithProjection as ClapTextModelWithProjection, __webpack_exports__ClassifierFreeGuidanceLogitsProcessor as ClassifierFreeGuidanceLogitsProcessor, __webpack_exports__CodeGenForCausalLM as CodeGenForCausalLM, __webpack_exports__CodeGenModel as CodeGenModel, __webpack_exports__CodeGenPreTrainedModel as CodeGenPreTrainedModel, __webpack_exports__CodeGenTokenizer as CodeGenTokenizer, __webpack_exports__CodeLlamaTokenizer as CodeLlamaTokenizer, __webpack_exports__CohereForCausalLM as CohereForCausalLM, __webpack_exports__CohereModel as CohereModel, __webpack_exports__CoherePreTrainedModel as CoherePreTrainedModel, __webpack_exports__CohereTokenizer as CohereTokenizer, __webpack_exports__ConvBertForMaskedLM as ConvBertForMaskedLM, __webpack_exports__ConvBertForQuestionAnswering as ConvBertForQuestionAnswering, __webpack_exports__ConvBertForSequenceClassification as ConvBertForSequenceClassification, __webpack_exports__ConvBertForTokenClassification as ConvBertForTokenClassification, __webpack_exports__ConvBertModel as ConvBertModel, __webpack_exports__ConvBertPreTrainedModel as ConvBertPreTrainedModel, __webpack_exports__ConvBertTokenizer as ConvBertTokenizer, __webpack_exports__ConvNextFeatureExtractor as ConvNextFeatureExtractor, __webpack_exports__ConvNextForImageClassification as ConvNextForImageClassification, __webpack_exports__ConvNextImageProcessor as ConvNextImageProcessor, __webpack_exports__ConvNextModel as ConvNextModel, __webpack_exports__ConvNextPreTrainedModel as ConvNextPreTrainedModel, __webpack_exports__ConvNextV2ForImageClassification as ConvNextV2ForImageClassification, __webpack_exports__ConvNextV2Model as ConvNextV2Model, __webpack_exports__ConvNextV2PreTrainedModel as ConvNextV2PreTrainedModel, __webpack_exports__DPTFeatureExtractor as DPTFeatureExtractor, __webpack_exports__DPTForDepthEstimation as DPTForDepthEstimation, __webpack_exports__DPTImageProcessor as DPTImageProcessor, __webpack_exports__DPTModel as DPTModel, __webpack_exports__DPTPreTrainedModel as DPTPreTrainedModel, __webpack_exports__DebertaForMaskedLM as DebertaForMaskedLM, __webpack_exports__DebertaForQuestionAnswering as DebertaForQuestionAnswering, __webpack_exports__DebertaForSequenceClassification as DebertaForSequenceClassification, __webpack_exports__DebertaForTokenClassification as DebertaForTokenClassification, __webpack_exports__DebertaModel as DebertaModel, __webpack_exports__DebertaPreTrainedModel as DebertaPreTrainedModel, __webpack_exports__DebertaTokenizer as DebertaTokenizer, __webpack_exports__DebertaV2ForMaskedLM as DebertaV2ForMaskedLM, __webpack_exports__DebertaV2ForQuestionAnswering as DebertaV2ForQuestionAnswering, __webpack_exports__DebertaV2ForSequenceClassification as DebertaV2ForSequenceClassification, __webpack_exports__DebertaV2ForTokenClassification as DebertaV2ForTokenClassification, __webpack_exports__DebertaV2Model as DebertaV2Model, __webpack_exports__DebertaV2PreTrainedModel as DebertaV2PreTrainedModel, __webpack_exports__DebertaV2Tokenizer as DebertaV2Tokenizer, __webpack_exports__DecisionTransformerModel as DecisionTransformerModel, __webpack_exports__DecisionTransformerPreTrainedModel as DecisionTransformerPreTrainedModel, __webpack_exports__DeiTFeatureExtractor as DeiTFeatureExtractor, __webpack_exports__DeiTForImageClassification as DeiTForImageClassification, __webpack_exports__DeiTImageProcessor as DeiTImageProcessor, __webpack_exports__DeiTModel as DeiTModel, __webpack_exports__DeiTPreTrainedModel as DeiTPreTrainedModel, __webpack_exports__DepthAnythingForDepthEstimation as DepthAnythingForDepthEstimation, __webpack_exports__DepthAnythingPreTrainedModel as DepthAnythingPreTrainedModel, __webpack_exports__DepthEstimationPipeline as DepthEstimationPipeline, __webpack_exports__DepthProForDepthEstimation as DepthProForDepthEstimation, __webpack_exports__DepthProPreTrainedModel as DepthProPreTrainedModel, __webpack_exports__DetrFeatureExtractor as DetrFeatureExtractor, __webpack_exports__DetrForObjectDetection as DetrForObjectDetection, __webpack_exports__DetrForSegmentation as DetrForSegmentation, __webpack_exports__DetrImageProcessor as DetrImageProcessor, __webpack_exports__DetrModel as DetrModel, __webpack_exports__DetrObjectDetectionOutput as DetrObjectDetectionOutput, __webpack_exports__DetrPreTrainedModel as DetrPreTrainedModel, __webpack_exports__DetrSegmentationOutput as DetrSegmentationOutput, __webpack_exports__Dinov2ForImageClassification as Dinov2ForImageClassification, __webpack_exports__Dinov2Model as Dinov2Model, __webpack_exports__Dinov2PreTrainedModel as Dinov2PreTrainedModel, __webpack_exports__DistilBertForMaskedLM as DistilBertForMaskedLM, __webpack_exports__DistilBertForQuestionAnswering as DistilBertForQuestionAnswering, __webpack_exports__DistilBertForSequenceClassification as DistilBertForSequenceClassification, __webpack_exports__DistilBertForTokenClassification as DistilBertForTokenClassification, __webpack_exports__DistilBertModel as DistilBertModel, __webpack_exports__DistilBertPreTrainedModel as DistilBertPreTrainedModel, __webpack_exports__DistilBertTokenizer as DistilBertTokenizer, __webpack_exports__DocumentQuestionAnsweringPipeline as DocumentQuestionAnsweringPipeline, __webpack_exports__DonutFeatureExtractor as DonutFeatureExtractor, __webpack_exports__DonutImageProcessor as DonutImageProcessor, __webpack_exports__DonutSwinModel as DonutSwinModel, __webpack_exports__DonutSwinPreTrainedModel as DonutSwinPreTrainedModel, __webpack_exports__EfficientNetForImageClassification as EfficientNetForImageClassification, __webpack_exports__EfficientNetImageProcessor as EfficientNetImageProcessor, __webpack_exports__EfficientNetModel as EfficientNetModel, __webpack_exports__EfficientNetPreTrainedModel as EfficientNetPreTrainedModel, __webpack_exports__ElectraForMaskedLM as ElectraForMaskedLM, __webpack_exports__ElectraForQuestionAnswering as ElectraForQuestionAnswering, __webpack_exports__ElectraForSequenceClassification as ElectraForSequenceClassification, __webpack_exports__ElectraForTokenClassification as ElectraForTokenClassification, __webpack_exports__ElectraModel as ElectraModel, __webpack_exports__ElectraPreTrainedModel as ElectraPreTrainedModel, __webpack_exports__ElectraTokenizer as ElectraTokenizer, __webpack_exports__EosTokenCriteria as EosTokenCriteria, __webpack_exports__EsmForMaskedLM as EsmForMaskedLM, __webpack_exports__EsmForSequenceClassification as EsmForSequenceClassification, __webpack_exports__EsmForTokenClassification as EsmForTokenClassification, __webpack_exports__EsmModel as EsmModel, __webpack_exports__EsmPreTrainedModel as EsmPreTrainedModel, __webpack_exports__EsmTokenizer as EsmTokenizer, __webpack_exports__FFT as FFT, __webpack_exports__FalconForCausalLM as FalconForCausalLM, __webpack_exports__FalconModel as FalconModel, __webpack_exports__FalconPreTrainedModel as FalconPreTrainedModel, __webpack_exports__FalconTokenizer as FalconTokenizer, __webpack_exports__FastViTForImageClassification as FastViTForImageClassification, __webpack_exports__FastViTModel as FastViTModel, __webpack_exports__FastViTPreTrainedModel as FastViTPreTrainedModel, __webpack_exports__FeatureExtractionPipeline as FeatureExtractionPipeline, __webpack_exports__FeatureExtractor as FeatureExtractor, __webpack_exports__FillMaskPipeline as FillMaskPipeline, __webpack_exports__Florence2ForConditionalGeneration as Florence2ForConditionalGeneration, __webpack_exports__Florence2PreTrainedModel as Florence2PreTrainedModel, __webpack_exports__Florence2Processor as Florence2Processor, __webpack_exports__ForcedBOSTokenLogitsProcessor as ForcedBOSTokenLogitsProcessor, __webpack_exports__ForcedEOSTokenLogitsProcessor as ForcedEOSTokenLogitsProcessor, __webpack_exports__GLPNFeatureExtractor as GLPNFeatureExtractor, __webpack_exports__GLPNForDepthEstimation as GLPNForDepthEstimation, __webpack_exports__GLPNModel as GLPNModel, __webpack_exports__GLPNPreTrainedModel as GLPNPreTrainedModel, __webpack_exports__GPT2LMHeadModel as GPT2LMHeadModel, __webpack_exports__GPT2Model as GPT2Model, __webpack_exports__GPT2PreTrainedModel as GPT2PreTrainedModel, __webpack_exports__GPT2Tokenizer as GPT2Tokenizer, __webpack_exports__GPTBigCodeForCausalLM as GPTBigCodeForCausalLM, __webpack_exports__GPTBigCodeModel as GPTBigCodeModel, __webpack_exports__GPTBigCodePreTrainedModel as GPTBigCodePreTrainedModel, __webpack_exports__GPTJForCausalLM as GPTJForCausalLM, __webpack_exports__GPTJModel as GPTJModel, __webpack_exports__GPTJPreTrainedModel as GPTJPreTrainedModel, __webpack_exports__GPTNeoForCausalLM as GPTNeoForCausalLM, __webpack_exports__GPTNeoModel as GPTNeoModel, __webpack_exports__GPTNeoPreTrainedModel as GPTNeoPreTrainedModel, __webpack_exports__GPTNeoXForCausalLM as GPTNeoXForCausalLM, __webpack_exports__GPTNeoXModel as GPTNeoXModel, __webpack_exports__GPTNeoXPreTrainedModel as GPTNeoXPreTrainedModel, __webpack_exports__GPTNeoXTokenizer as GPTNeoXTokenizer, __webpack_exports__Gemma2ForCausalLM as Gemma2ForCausalLM, __webpack_exports__Gemma2Model as Gemma2Model, __webpack_exports__Gemma2PreTrainedModel as Gemma2PreTrainedModel, __webpack_exports__GemmaForCausalLM as GemmaForCausalLM, __webpack_exports__GemmaModel as GemmaModel, __webpack_exports__GemmaPreTrainedModel as GemmaPreTrainedModel, __webpack_exports__GemmaTokenizer as GemmaTokenizer, __webpack_exports__GraniteForCausalLM as GraniteForCausalLM, __webpack_exports__GraniteModel as GraniteModel, __webpack_exports__GranitePreTrainedModel as GranitePreTrainedModel, __webpack_exports__Grok1Tokenizer as Grok1Tokenizer, __webpack_exports__GroupViTModel as GroupViTModel, __webpack_exports__GroupViTPreTrainedModel as GroupViTPreTrainedModel, __webpack_exports__HerbertTokenizer as HerbertTokenizer, __webpack_exports__HieraForImageClassification as HieraForImageClassification, __webpack_exports__HieraModel as HieraModel, __webpack_exports__HieraPreTrainedModel as HieraPreTrainedModel, __webpack_exports__HubertForCTC as HubertForCTC, __webpack_exports__HubertForSequenceClassification as HubertForSequenceClassification, __webpack_exports__HubertModel as HubertModel, __webpack_exports__HubertPreTrainedModel as HubertPreTrainedModel, __webpack_exports__IJepaForImageClassification as IJepaForImageClassification, __webpack_exports__IJepaModel as IJepaModel, __webpack_exports__IJepaPreTrainedModel as IJepaPreTrainedModel, __webpack_exports__Idefics3ForConditionalGeneration as Idefics3ForConditionalGeneration, __webpack_exports__Idefics3ImageProcessor as Idefics3ImageProcessor, __webpack_exports__Idefics3PreTrainedModel as Idefics3PreTrainedModel, __webpack_exports__Idefics3Processor as Idefics3Processor, __webpack_exports__ImageClassificationPipeline as ImageClassificationPipeline, __webpack_exports__ImageFeatureExtractionPipeline as ImageFeatureExtractionPipeline, __webpack_exports__ImageFeatureExtractor as ImageFeatureExtractor, __webpack_exports__ImageMattingOutput as ImageMattingOutput, __webpack_exports__ImageProcessor as ImageProcessor, __webpack_exports__ImageSegmentationPipeline as ImageSegmentationPipeline, __webpack_exports__ImageToImagePipeline as ImageToImagePipeline, __webpack_exports__ImageToTextPipeline as ImageToTextPipeline, __webpack_exports__InterruptableStoppingCriteria as InterruptableStoppingCriteria, __webpack_exports__JAISLMHeadModel as JAISLMHeadModel, __webpack_exports__JAISModel as JAISModel, __webpack_exports__JAISPreTrainedModel as JAISPreTrainedModel, __webpack_exports__JinaCLIPImageProcessor as JinaCLIPImageProcessor, __webpack_exports__JinaCLIPModel as JinaCLIPModel, __webpack_exports__JinaCLIPPreTrainedModel as JinaCLIPPreTrainedModel, __webpack_exports__JinaCLIPProcessor as JinaCLIPProcessor, __webpack_exports__JinaCLIPTextModel as JinaCLIPTextModel, __webpack_exports__JinaCLIPVisionModel as JinaCLIPVisionModel, __webpack_exports__LlamaForCausalLM as LlamaForCausalLM, __webpack_exports__LlamaModel as LlamaModel, __webpack_exports__LlamaPreTrainedModel as LlamaPreTrainedModel, __webpack_exports__LlamaTokenizer as LlamaTokenizer, __webpack_exports__LlavaForConditionalGeneration as LlavaForConditionalGeneration, __webpack_exports__LlavaOnevisionForConditionalGeneration as LlavaOnevisionForConditionalGeneration, __webpack_exports__LlavaOnevisionImageProcessor as LlavaOnevisionImageProcessor, __webpack_exports__LlavaPreTrainedModel as LlavaPreTrainedModel, __webpack_exports__LogitsProcessor as LogitsProcessor, __webpack_exports__LogitsProcessorList as LogitsProcessorList, __webpack_exports__LogitsWarper as LogitsWarper, __webpack_exports__LongT5ForConditionalGeneration as LongT5ForConditionalGeneration, __webpack_exports__LongT5Model as LongT5Model, __webpack_exports__LongT5PreTrainedModel as LongT5PreTrainedModel, __webpack_exports__M2M100ForConditionalGeneration as M2M100ForConditionalGeneration, __webpack_exports__M2M100Model as M2M100Model, __webpack_exports__M2M100PreTrainedModel as M2M100PreTrainedModel, __webpack_exports__M2M100Tokenizer as M2M100Tokenizer, __webpack_exports__MBart50Tokenizer as MBart50Tokenizer, __webpack_exports__MBartForCausalLM as MBartForCausalLM, __webpack_exports__MBartForConditionalGeneration as MBartForConditionalGeneration, __webpack_exports__MBartForSequenceClassification as MBartForSequenceClassification, __webpack_exports__MBartModel as MBartModel, __webpack_exports__MBartPreTrainedModel as MBartPreTrainedModel, __webpack_exports__MBartTokenizer as MBartTokenizer, __webpack_exports__MPNetForMaskedLM as MPNetForMaskedLM, __webpack_exports__MPNetForQuestionAnswering as MPNetForQuestionAnswering, __webpack_exports__MPNetForSequenceClassification as MPNetForSequenceClassification, __webpack_exports__MPNetForTokenClassification as MPNetForTokenClassification, __webpack_exports__MPNetModel as MPNetModel, __webpack_exports__MPNetPreTrainedModel as MPNetPreTrainedModel, __webpack_exports__MPNetTokenizer as MPNetTokenizer, __webpack_exports__MT5ForConditionalGeneration as MT5ForConditionalGeneration, __webpack_exports__MT5Model as MT5Model, __webpack_exports__MT5PreTrainedModel as MT5PreTrainedModel, __webpack_exports__MarianMTModel as MarianMTModel, __webpack_exports__MarianModel as MarianModel, __webpack_exports__MarianPreTrainedModel as MarianPreTrainedModel, __webpack_exports__MarianTokenizer as MarianTokenizer, __webpack_exports__Mask2FormerImageProcessor as Mask2FormerImageProcessor, __webpack_exports__MaskFormerFeatureExtractor as MaskFormerFeatureExtractor, __webpack_exports__MaskFormerForInstanceSegmentation as MaskFormerForInstanceSegmentation, __webpack_exports__MaskFormerImageProcessor as MaskFormerImageProcessor, __webpack_exports__MaskFormerModel as MaskFormerModel, __webpack_exports__MaskFormerPreTrainedModel as MaskFormerPreTrainedModel, __webpack_exports__MaskedLMOutput as MaskedLMOutput, __webpack_exports__MaxLengthCriteria as MaxLengthCriteria, __webpack_exports__MgpstrForSceneTextRecognition as MgpstrForSceneTextRecognition, __webpack_exports__MgpstrModelOutput as MgpstrModelOutput, __webpack_exports__MgpstrPreTrainedModel as MgpstrPreTrainedModel, __webpack_exports__MgpstrProcessor as MgpstrProcessor, __webpack_exports__MgpstrTokenizer as MgpstrTokenizer, __webpack_exports__MinLengthLogitsProcessor as MinLengthLogitsProcessor, __webpack_exports__MinNewTokensLengthLogitsProcessor as MinNewTokensLengthLogitsProcessor, __webpack_exports__MistralForCausalLM as MistralForCausalLM, __webpack_exports__MistralModel as MistralModel, __webpack_exports__MistralPreTrainedModel as MistralPreTrainedModel, __webpack_exports__MobileBertForMaskedLM as MobileBertForMaskedLM, __webpack_exports__MobileBertForQuestionAnswering as MobileBertForQuestionAnswering, __webpack_exports__MobileBertForSequenceClassification as MobileBertForSequenceClassification, __webpack_exports__MobileBertModel as MobileBertModel, __webpack_exports__MobileBertPreTrainedModel as MobileBertPreTrainedModel, __webpack_exports__MobileBertTokenizer as MobileBertTokenizer, __webpack_exports__MobileLLMForCausalLM as MobileLLMForCausalLM, __webpack_exports__MobileLLMModel as MobileLLMModel, __webpack_exports__MobileLLMPreTrainedModel as MobileLLMPreTrainedModel, __webpack_exports__MobileNetV1FeatureExtractor as MobileNetV1FeatureExtractor, __webpack_exports__MobileNetV1ForImageClassification as MobileNetV1ForImageClassification, __webpack_exports__MobileNetV1ImageProcessor as MobileNetV1ImageProcessor, __webpack_exports__MobileNetV1Model as MobileNetV1Model, __webpack_exports__MobileNetV1PreTrainedModel as MobileNetV1PreTrainedModel, __webpack_exports__MobileNetV2FeatureExtractor as MobileNetV2FeatureExtractor, __webpack_exports__MobileNetV2ForImageClassification as MobileNetV2ForImageClassification, __webpack_exports__MobileNetV2ImageProcessor as MobileNetV2ImageProcessor, __webpack_exports__MobileNetV2Model as MobileNetV2Model, __webpack_exports__MobileNetV2PreTrainedModel as MobileNetV2PreTrainedModel, __webpack_exports__MobileNetV3FeatureExtractor as MobileNetV3FeatureExtractor, __webpack_exports__MobileNetV3ForImageClassification as MobileNetV3ForImageClassification, __webpack_exports__MobileNetV3ImageProcessor as MobileNetV3ImageProcessor, __webpack_exports__MobileNetV3Model as MobileNetV3Model, __webpack_exports__MobileNetV3PreTrainedModel as MobileNetV3PreTrainedModel, __webpack_exports__MobileNetV4FeatureExtractor as MobileNetV4FeatureExtractor, __webpack_exports__MobileNetV4ForImageClassification as MobileNetV4ForImageClassification, __webpack_exports__MobileNetV4ImageProcessor as MobileNetV4ImageProcessor, __webpack_exports__MobileNetV4Model as MobileNetV4Model, __webpack_exports__MobileNetV4PreTrainedModel as MobileNetV4PreTrainedModel, __webpack_exports__MobileViTFeatureExtractor as MobileViTFeatureExtractor, __webpack_exports__MobileViTForImageClassification as MobileViTForImageClassification, __webpack_exports__MobileViTImageProcessor as MobileViTImageProcessor, __webpack_exports__MobileViTModel as MobileViTModel, __webpack_exports__MobileViTPreTrainedModel as MobileViTPreTrainedModel, __webpack_exports__MobileViTV2ForImageClassification as MobileViTV2ForImageClassification, __webpack_exports__MobileViTV2Model as MobileViTV2Model, __webpack_exports__MobileViTV2PreTrainedModel as MobileViTV2PreTrainedModel, __webpack_exports__ModelOutput as ModelOutput, __webpack_exports__Moondream1ForConditionalGeneration as Moondream1ForConditionalGeneration, __webpack_exports__MptForCausalLM as MptForCausalLM, __webpack_exports__MptModel as MptModel, __webpack_exports__MptPreTrainedModel as MptPreTrainedModel, __webpack_exports__MultiModalityCausalLM as MultiModalityCausalLM, __webpack_exports__MultiModalityPreTrainedModel as MultiModalityPreTrainedModel, __webpack_exports__MusicgenForCausalLM as MusicgenForCausalLM, __webpack_exports__MusicgenForConditionalGeneration as MusicgenForConditionalGeneration, __webpack_exports__MusicgenModel as MusicgenModel, __webpack_exports__MusicgenPreTrainedModel as MusicgenPreTrainedModel, __webpack_exports__NllbTokenizer as NllbTokenizer, __webpack_exports__NoBadWordsLogitsProcessor as NoBadWordsLogitsProcessor, __webpack_exports__NoRepeatNGramLogitsProcessor as NoRepeatNGramLogitsProcessor, __webpack_exports__NomicBertModel as NomicBertModel, __webpack_exports__NomicBertPreTrainedModel as NomicBertPreTrainedModel, __webpack_exports__NougatImageProcessor as NougatImageProcessor, __webpack_exports__NougatTokenizer as NougatTokenizer, __webpack_exports__OPTForCausalLM as OPTForCausalLM, __webpack_exports__OPTModel as OPTModel, __webpack_exports__OPTPreTrainedModel as OPTPreTrainedModel, __webpack_exports__ObjectDetectionPipeline as ObjectDetectionPipeline, __webpack_exports__Olmo2ForCausalLM as Olmo2ForCausalLM, __webpack_exports__Olmo2Model as Olmo2Model, __webpack_exports__Olmo2PreTrainedModel as Olmo2PreTrainedModel, __webpack_exports__OlmoForCausalLM as OlmoForCausalLM, __webpack_exports__OlmoModel as OlmoModel, __webpack_exports__OlmoPreTrainedModel as OlmoPreTrainedModel, __webpack_exports__OpenELMForCausalLM as OpenELMForCausalLM, __webpack_exports__OpenELMModel as OpenELMModel, __webpack_exports__OpenELMPreTrainedModel as OpenELMPreTrainedModel, __webpack_exports__OwlViTFeatureExtractor as OwlViTFeatureExtractor, __webpack_exports__OwlViTForObjectDetection as OwlViTForObjectDetection, __webpack_exports__OwlViTImageProcessor as OwlViTImageProcessor, __webpack_exports__OwlViTModel as OwlViTModel, __webpack_exports__OwlViTPreTrainedModel as OwlViTPreTrainedModel, __webpack_exports__OwlViTProcessor as OwlViTProcessor, __webpack_exports__Owlv2ForObjectDetection as Owlv2ForObjectDetection, __webpack_exports__Owlv2ImageProcessor as Owlv2ImageProcessor, __webpack_exports__Owlv2Model as Owlv2Model, __webpack_exports__Owlv2PreTrainedModel as Owlv2PreTrainedModel, __webpack_exports__PaliGemmaForConditionalGeneration as PaliGemmaForConditionalGeneration, __webpack_exports__PaliGemmaPreTrainedModel as PaliGemmaPreTrainedModel, __webpack_exports__PaliGemmaProcessor as PaliGemmaProcessor, __webpack_exports__PatchTSMixerForPrediction as PatchTSMixerForPrediction, __webpack_exports__PatchTSMixerModel as PatchTSMixerModel, __webpack_exports__PatchTSMixerPreTrainedModel as PatchTSMixerPreTrainedModel, __webpack_exports__PatchTSTForPrediction as PatchTSTForPrediction, __webpack_exports__PatchTSTModel as PatchTSTModel, __webpack_exports__PatchTSTPreTrainedModel as PatchTSTPreTrainedModel, __webpack_exports__Phi3ForCausalLM as Phi3ForCausalLM, __webpack_exports__Phi3Model as Phi3Model, __webpack_exports__Phi3PreTrainedModel as Phi3PreTrainedModel, __webpack_exports__PhiForCausalLM as PhiForCausalLM, __webpack_exports__PhiModel as PhiModel, __webpack_exports__PhiPreTrainedModel as PhiPreTrainedModel, __webpack_exports__Pipeline as Pipeline, __webpack_exports__PreTrainedModel as PreTrainedModel, __webpack_exports__PreTrainedTokenizer as PreTrainedTokenizer, __webpack_exports__PretrainedConfig as PretrainedConfig, __webpack_exports__PretrainedMixin as PretrainedMixin, __webpack_exports__Processor as Processor, __webpack_exports__PvtForImageClassification as PvtForImageClassification, __webpack_exports__PvtImageProcessor as PvtImageProcessor, __webpack_exports__PvtModel as PvtModel, __webpack_exports__PvtPreTrainedModel as PvtPreTrainedModel, __webpack_exports__PyAnnoteFeatureExtractor as PyAnnoteFeatureExtractor, __webpack_exports__PyAnnoteForAudioFrameClassification as PyAnnoteForAudioFrameClassification, __webpack_exports__PyAnnoteModel as PyAnnoteModel, __webpack_exports__PyAnnotePreTrainedModel as PyAnnotePreTrainedModel, __webpack_exports__PyAnnoteProcessor as PyAnnoteProcessor, __webpack_exports__QuestionAnsweringModelOutput as QuestionAnsweringModelOutput, __webpack_exports__QuestionAnsweringPipeline as QuestionAnsweringPipeline, __webpack_exports__Qwen2ForCausalLM as Qwen2ForCausalLM, __webpack_exports__Qwen2Model as Qwen2Model, __webpack_exports__Qwen2PreTrainedModel as Qwen2PreTrainedModel, __webpack_exports__Qwen2Tokenizer as Qwen2Tokenizer, __webpack_exports__Qwen2VLForConditionalGeneration as Qwen2VLForConditionalGeneration, __webpack_exports__Qwen2VLImageProcessor as Qwen2VLImageProcessor, __webpack_exports__Qwen2VLPreTrainedModel as Qwen2VLPreTrainedModel, __webpack_exports__Qwen2VLProcessor as Qwen2VLProcessor, __webpack_exports__RTDetrForObjectDetection as RTDetrForObjectDetection, __webpack_exports__RTDetrImageProcessor as RTDetrImageProcessor, __webpack_exports__RTDetrModel as RTDetrModel, __webpack_exports__RTDetrObjectDetectionOutput as RTDetrObjectDetectionOutput, __webpack_exports__RTDetrPreTrainedModel as RTDetrPreTrainedModel, __webpack_exports__RawImage as RawImage, __webpack_exports__RepetitionPenaltyLogitsProcessor as RepetitionPenaltyLogitsProcessor, __webpack_exports__ResNetForImageClassification as ResNetForImageClassification, __webpack_exports__ResNetModel as ResNetModel, __webpack_exports__ResNetPreTrainedModel as ResNetPreTrainedModel, __webpack_exports__RoFormerForMaskedLM as RoFormerForMaskedLM, __webpack_exports__RoFormerForQuestionAnswering as RoFormerForQuestionAnswering, __webpack_exports__RoFormerForSequenceClassification as RoFormerForSequenceClassification, __webpack_exports__RoFormerForTokenClassification as RoFormerForTokenClassification, __webpack_exports__RoFormerModel as RoFormerModel, __webpack_exports__RoFormerPreTrainedModel as RoFormerPreTrainedModel, __webpack_exports__RoFormerTokenizer as RoFormerTokenizer, __webpack_exports__RobertaForMaskedLM as RobertaForMaskedLM, __webpack_exports__RobertaForQuestionAnswering as RobertaForQuestionAnswering, __webpack_exports__RobertaForSequenceClassification as RobertaForSequenceClassification, __webpack_exports__RobertaForTokenClassification as RobertaForTokenClassification, __webpack_exports__RobertaModel as RobertaModel, __webpack_exports__RobertaPreTrainedModel as RobertaPreTrainedModel, __webpack_exports__RobertaTokenizer as RobertaTokenizer, __webpack_exports__SamImageProcessor as SamImageProcessor, __webpack_exports__SamImageSegmentationOutput as SamImageSegmentationOutput, __webpack_exports__SamModel as SamModel, __webpack_exports__SamPreTrainedModel as SamPreTrainedModel, __webpack_exports__SamProcessor as SamProcessor, __webpack_exports__SapiensForDepthEstimation as SapiensForDepthEstimation, __webpack_exports__SapiensForNormalEstimation as SapiensForNormalEstimation, __webpack_exports__SapiensForSemanticSegmentation as SapiensForSemanticSegmentation, __webpack_exports__SapiensPreTrainedModel as SapiensPreTrainedModel, __webpack_exports__SeamlessM4TFeatureExtractor as SeamlessM4TFeatureExtractor, __webpack_exports__SegformerFeatureExtractor as SegformerFeatureExtractor, __webpack_exports__SegformerForImageClassification as SegformerForImageClassification, __webpack_exports__SegformerForSemanticSegmentation as SegformerForSemanticSegmentation, __webpack_exports__SegformerImageProcessor as SegformerImageProcessor, __webpack_exports__SegformerModel as SegformerModel, __webpack_exports__SegformerPreTrainedModel as SegformerPreTrainedModel, __webpack_exports__Seq2SeqLMOutput as Seq2SeqLMOutput, __webpack_exports__SequenceClassifierOutput as SequenceClassifierOutput, __webpack_exports__SiglipImageProcessor as SiglipImageProcessor, __webpack_exports__SiglipModel as SiglipModel, __webpack_exports__SiglipPreTrainedModel as SiglipPreTrainedModel, __webpack_exports__SiglipTextModel as SiglipTextModel, __webpack_exports__SiglipTokenizer as SiglipTokenizer, __webpack_exports__SiglipVisionModel as SiglipVisionModel, __webpack_exports__SpeechT5FeatureExtractor as SpeechT5FeatureExtractor, __webpack_exports__SpeechT5ForSpeechToText as SpeechT5ForSpeechToText, __webpack_exports__SpeechT5ForTextToSpeech as SpeechT5ForTextToSpeech, __webpack_exports__SpeechT5HifiGan as SpeechT5HifiGan, __webpack_exports__SpeechT5Model as SpeechT5Model, __webpack_exports__SpeechT5PreTrainedModel as SpeechT5PreTrainedModel, __webpack_exports__SpeechT5Processor as SpeechT5Processor, __webpack_exports__SpeechT5Tokenizer as SpeechT5Tokenizer, __webpack_exports__SqueezeBertForMaskedLM as SqueezeBertForMaskedLM, __webpack_exports__SqueezeBertForQuestionAnswering as SqueezeBertForQuestionAnswering, __webpack_exports__SqueezeBertForSequenceClassification as SqueezeBertForSequenceClassification, __webpack_exports__SqueezeBertModel as SqueezeBertModel, __webpack_exports__SqueezeBertPreTrainedModel as SqueezeBertPreTrainedModel, __webpack_exports__SqueezeBertTokenizer as SqueezeBertTokenizer, __webpack_exports__StableLmForCausalLM as StableLmForCausalLM, __webpack_exports__StableLmModel as StableLmModel, __webpack_exports__StableLmPreTrainedModel as StableLmPreTrainedModel, __webpack_exports__Starcoder2ForCausalLM as Starcoder2ForCausalLM, __webpack_exports__Starcoder2Model as Starcoder2Model, __webpack_exports__Starcoder2PreTrainedModel as Starcoder2PreTrainedModel, __webpack_exports__StoppingCriteria as StoppingCriteria, __webpack_exports__StoppingCriteriaList as StoppingCriteriaList, __webpack_exports__SummarizationPipeline as SummarizationPipeline, __webpack_exports__SuppressTokensAtBeginLogitsProcessor as SuppressTokensAtBeginLogitsProcessor, __webpack_exports__Swin2SRForImageSuperResolution as Swin2SRForImageSuperResolution, __webpack_exports__Swin2SRImageProcessor as Swin2SRImageProcessor, __webpack_exports__Swin2SRModel as Swin2SRModel, __webpack_exports__Swin2SRPreTrainedModel as Swin2SRPreTrainedModel, __webpack_exports__SwinForImageClassification as SwinForImageClassification, __webpack_exports__SwinModel as SwinModel, __webpack_exports__SwinPreTrainedModel as SwinPreTrainedModel, __webpack_exports__T5ForConditionalGeneration as T5ForConditionalGeneration, __webpack_exports__T5Model as T5Model, __webpack_exports__T5PreTrainedModel as T5PreTrainedModel, __webpack_exports__T5Tokenizer as T5Tokenizer, __webpack_exports__TableTransformerForObjectDetection as TableTransformerForObjectDetection, __webpack_exports__TableTransformerModel as TableTransformerModel, __webpack_exports__TableTransformerObjectDetectionOutput as TableTransformerObjectDetectionOutput, __webpack_exports__TableTransformerPreTrainedModel as TableTransformerPreTrainedModel, __webpack_exports__TemperatureLogitsWarper as TemperatureLogitsWarper, __webpack_exports__Tensor as Tensor, __webpack_exports__Text2TextGenerationPipeline as Text2TextGenerationPipeline, __webpack_exports__TextClassificationPipeline as TextClassificationPipeline, __webpack_exports__TextGenerationPipeline as TextGenerationPipeline, __webpack_exports__TextStreamer as TextStreamer, __webpack_exports__TextToAudioPipeline as TextToAudioPipeline, __webpack_exports__TokenClassificationPipeline as TokenClassificationPipeline, __webpack_exports__TokenClassifierOutput as TokenClassifierOutput, __webpack_exports__TokenizerModel as TokenizerModel, __webpack_exports__TopKLogitsWarper as TopKLogitsWarper, __webpack_exports__TopPLogitsWarper as TopPLogitsWarper, __webpack_exports__TrOCRForCausalLM as TrOCRForCausalLM, __webpack_exports__TrOCRPreTrainedModel as TrOCRPreTrainedModel, __webpack_exports__TranslationPipeline as TranslationPipeline, __webpack_exports__UniSpeechForCTC as UniSpeechForCTC, __webpack_exports__UniSpeechForSequenceClassification as UniSpeechForSequenceClassification, __webpack_exports__UniSpeechModel as UniSpeechModel, __webpack_exports__UniSpeechPreTrainedModel as UniSpeechPreTrainedModel, __webpack_exports__UniSpeechSatForAudioFrameClassification as UniSpeechSatForAudioFrameClassification, __webpack_exports__UniSpeechSatForCTC as UniSpeechSatForCTC, __webpack_exports__UniSpeechSatForSequenceClassification as UniSpeechSatForSequenceClassification, __webpack_exports__UniSpeechSatModel as UniSpeechSatModel, __webpack_exports__UniSpeechSatPreTrainedModel as UniSpeechSatPreTrainedModel, __webpack_exports__VLChatProcessor as VLChatProcessor, __webpack_exports__VLMImageProcessor as VLMImageProcessor, __webpack_exports__ViTFeatureExtractor as ViTFeatureExtractor, __webpack_exports__ViTForImageClassification as ViTForImageClassification, __webpack_exports__ViTImageProcessor as ViTImageProcessor, __webpack_exports__ViTMAEModel as ViTMAEModel, __webpack_exports__ViTMAEPreTrainedModel as ViTMAEPreTrainedModel, __webpack_exports__ViTMSNForImageClassification as ViTMSNForImageClassification, __webpack_exports__ViTMSNModel as ViTMSNModel, __webpack_exports__ViTMSNPreTrainedModel as ViTMSNPreTrainedModel, __webpack_exports__ViTModel as ViTModel, __webpack_exports__ViTPreTrainedModel as ViTPreTrainedModel, __webpack_exports__VisionEncoderDecoderModel as VisionEncoderDecoderModel, __webpack_exports__VitMatteForImageMatting as VitMatteForImageMatting, __webpack_exports__VitMatteImageProcessor as VitMatteImageProcessor, __webpack_exports__VitMattePreTrainedModel as VitMattePreTrainedModel, __webpack_exports__VitPoseForPoseEstimation as VitPoseForPoseEstimation, __webpack_exports__VitPoseImageProcessor as VitPoseImageProcessor, __webpack_exports__VitPosePreTrainedModel as VitPosePreTrainedModel, __webpack_exports__VitsModel as VitsModel, __webpack_exports__VitsModelOutput as VitsModelOutput, __webpack_exports__VitsPreTrainedModel as VitsPreTrainedModel, __webpack_exports__VitsTokenizer as VitsTokenizer, __webpack_exports__Wav2Vec2BertForCTC as Wav2Vec2BertForCTC, __webpack_exports__Wav2Vec2BertForSequenceClassification as Wav2Vec2BertForSequenceClassification, __webpack_exports__Wav2Vec2BertModel as Wav2Vec2BertModel, __webpack_exports__Wav2Vec2BertPreTrainedModel as Wav2Vec2BertPreTrainedModel, __webpack_exports__Wav2Vec2CTCTokenizer as Wav2Vec2CTCTokenizer, __webpack_exports__Wav2Vec2FeatureExtractor as Wav2Vec2FeatureExtractor, __webpack_exports__Wav2Vec2ForAudioFrameClassification as Wav2Vec2ForAudioFrameClassification, __webpack_exports__Wav2Vec2ForCTC as Wav2Vec2ForCTC, __webpack_exports__Wav2Vec2ForSequenceClassification as Wav2Vec2ForSequenceClassification, __webpack_exports__Wav2Vec2Model as Wav2Vec2Model, __webpack_exports__Wav2Vec2PreTrainedModel as Wav2Vec2PreTrainedModel, __webpack_exports__Wav2Vec2ProcessorWithLM as Wav2Vec2ProcessorWithLM, __webpack_exports__WavLMForAudioFrameClassification as WavLMForAudioFrameClassification, __webpack_exports__WavLMForCTC as WavLMForCTC, __webpack_exports__WavLMForSequenceClassification as WavLMForSequenceClassification, __webpack_exports__WavLMForXVector as WavLMForXVector, __webpack_exports__WavLMModel as WavLMModel, __webpack_exports__WavLMPreTrainedModel as WavLMPreTrainedModel, __webpack_exports__WeSpeakerFeatureExtractor as WeSpeakerFeatureExtractor, __webpack_exports__WeSpeakerResNetModel as WeSpeakerResNetModel, __webpack_exports__WeSpeakerResNetPreTrainedModel as WeSpeakerResNetPreTrainedModel, __webpack_exports__WhisperFeatureExtractor as WhisperFeatureExtractor, __webpack_exports__WhisperForConditionalGeneration as WhisperForConditionalGeneration, __webpack_exports__WhisperModel as WhisperModel, __webpack_exports__WhisperPreTrainedModel as WhisperPreTrainedModel, __webpack_exports__WhisperProcessor as WhisperProcessor, __webpack_exports__WhisperTextStreamer as WhisperTextStreamer, __webpack_exports__WhisperTimeStampLogitsProcessor as WhisperTimeStampLogitsProcessor, __webpack_exports__WhisperTokenizer as WhisperTokenizer, __webpack_exports__XLMForQuestionAnswering as XLMForQuestionAnswering, __webpack_exports__XLMForSequenceClassification as XLMForSequenceClassification, __webpack_exports__XLMForTokenClassification as XLMForTokenClassification, __webpack_exports__XLMModel as XLMModel, __webpack_exports__XLMPreTrainedModel as XLMPreTrainedModel, __webpack_exports__XLMRobertaForMaskedLM as XLMRobertaForMaskedLM, __webpack_exports__XLMRobertaForQuestionAnswering as XLMRobertaForQuestionAnswering, __webpack_exports__XLMRobertaForSequenceClassification as XLMRobertaForSequenceClassification, __webpack_exports__XLMRobertaForTokenClassification as XLMRobertaForTokenClassification, __webpack_exports__XLMRobertaModel as XLMRobertaModel, __webpack_exports__XLMRobertaPreTrainedModel as XLMRobertaPreTrainedModel, __webpack_exports__XLMRobertaTokenizer as XLMRobertaTokenizer, __webpack_exports__XLMTokenizer as XLMTokenizer, __webpack_exports__XLMWithLMHeadModel as XLMWithLMHeadModel, __webpack_exports__XVectorOutput as XVectorOutput, __webpack_exports__YolosFeatureExtractor as YolosFeatureExtractor, __webpack_exports__YolosForObjectDetection as YolosForObjectDetection, __webpack_exports__YolosImageProcessor as YolosImageProcessor, __webpack_exports__YolosModel as YolosModel, __webpack_exports__YolosObjectDetectionOutput as YolosObjectDetectionOutput, __webpack_exports__YolosPreTrainedModel as YolosPreTrainedModel, __webpack_exports__ZeroShotAudioClassificationPipeline as ZeroShotAudioClassificationPipeline, __webpack_exports__ZeroShotClassificationPipeline as ZeroShotClassificationPipeline, __webpack_exports__ZeroShotImageClassificationPipeline as ZeroShotImageClassificationPipeline, __webpack_exports__ZeroShotObjectDetectionPipeline as ZeroShotObjectDetectionPipeline, __webpack_exports__bankers_round as bankers_round, __webpack_exports__cat as cat, __webpack_exports__cos_sim as cos_sim, __webpack_exports__dot as dot, __webpack_exports__dynamic_time_warping as dynamic_time_warping, __webpack_exports__env as env, __webpack_exports__full as full, __webpack_exports__full_like as full_like, __webpack_exports__getKeyValueShapes as getKeyValueShapes, __webpack_exports__hamming as hamming, __webpack_exports__hanning as hanning, __webpack_exports__interpolate as interpolate, __webpack_exports__interpolate_4d as interpolate_4d, __webpack_exports__interpolate_data as interpolate_data, __webpack_exports__is_chinese_char as is_chinese_char, __webpack_exports__layer_norm as layer_norm, __webpack_exports__load_image as load_image, __webpack_exports__log_softmax as log_softmax, __webpack_exports__magnitude as magnitude, __webpack_exports__matmul as matmul, __webpack_exports__max as max, __webpack_exports__mean as mean, __webpack_exports__mean_pooling as mean_pooling, __webpack_exports__medianFilter as medianFilter, __webpack_exports__mel_filter_bank as mel_filter_bank, __webpack_exports__min as min, __webpack_exports__ones as ones, __webpack_exports__ones_like as ones_like, __webpack_exports__permute as permute, __webpack_exports__permute_data as permute_data, __webpack_exports__pipeline as pipeline, __webpack_exports__quantize_embeddings as quantize_embeddings, __webpack_exports__read_audio as read_audio, __webpack_exports__rfft as rfft, __webpack_exports__round as round, __webpack_exports__softmax as softmax, __webpack_exports__spectrogram as spectrogram, __webpack_exports__stack as stack, __webpack_exports__std_mean as std_mean, __webpack_exports__topk as topk, __webpack_exports__window_function as window_function, __webpack_exports__zeros as zeros, __webpack_exports__zeros_like as zeros_like };
 
 //# sourceMappingURL=transformers.mjs.map