anyformer 0.4.11 → 0.4.12

package/CHANGELOG.md

@@ -1,5 +1,23 @@
 # Changelog
 
+## 0.4.12 — 2026-10-29
+
+### Changed
+- transformers.js pin 4.3.1 → 4.3.2 (in step with LocalMind), which adds `model_type` `lfm3` and `lfm3_vl`.
+- transformers back end: a graph whose last-position input is named `logits_to_keep` (LiquidAI's LFM3 ONNX export)
+  gets it fed at the session's run; transformers.js 4.3.2 feeds only `num_logits_to_keep` and stopped with "Missing
+  the following inputs". `LiquidAI/LFM3-1.7B-ONNX` now loads and generates through `chat.html` (64 tokens at
+  67 tok/s, Chrome, this Mac, 2026-10-28).
+- transformers back end, text pipeline path: `thinking: false` by default, as on every other back end. The template
+  renders with `enable_thinking` off (through `tokenizer_encode_kwargs`), so LFM3 answers directly; `thinking: true`
+  per request turns it on. Templates without the switch ignore it.
+- `test/browser/chat.html` takes `?dtype=` and fails a reply that contains `<think>` text.
+
+### Added
+- `MODELS.chat.LFM3_1_7B`: `LiquidAI/LFM3-1.7B-ONNX` on `transformers` (asked for by LocalMind for Chirag). Browser
+  chat check on 2026-10-29, Chrome, this Mac: on topic, no `<think>` text, on q4 (anyformer's pick, 1.63 GB; 82.4
+  tok/s) and on q4f16 (`dtype: 'q4f16'`, LocalMind's precision, 1.38 GB; 76.6 tok/s), the same 61-token reply.
+
 ## 0.4.11 — 2026-10-24
 
 ### Added

package/README.md

@@ -54,7 +54,7 @@ back end's answer: yes with an estimate (GPU bytes, disk bytes, tok/s when measu
 
 | Back end | Runs | Models |
 |---|---|---|
-| `transformers` | transformers.js 4.3.1: text generation (Nemotron 3.5 Bolt E4B among them), image and audio chat (Gemma 4, Qwen3.5), embeddings, speech to text, detection, classification, depth, segmentation | ONNX repos in the onnx-community / Xenova layout |
+| `transformers` | transformers.js 4.3.2: text generation (Nemotron 3.5 Bolt E4B and LFM3 1.7B among them), image and audio chat (Gemma 4, Qwen3.5), embeddings, speech to text, detection, classification, depth, segmentation | ONNX repos in the onnx-community / Xenova layout |
 | `kohra` | kohra, text-diffusion over onnxruntime-web | MDLM and BD3LM repos tagged `text-diffusion`; Nemotron-Labs-Diffusion-3B |
 | `localmind` | LocalMind's hand-written WebGPU kernels (shipped in diskformer), the whole model on the GPU | any LFM2 / LFM2.5 GGUF; Gemma 4 E2B / E4B QAT-mobile; Ternary Bonsai 2 |
 | `wllama` | llama.cpp in WebAssembly: WebGPU when the budget holds the model, the CPU otherwise (no WebGPU needed) | any GGUF up to about 3.6 GB that no engine above covers; files over 2 GB are split into OPFS shards once |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "anyformer",
-  "version": "0.4.11",
+  "version": "0.4.12",
   "description": "One call to run a model in a browser tab: anyformer reads the Hub repo, probes the browser, and picks the back end (transformers.js, LocalMind's WebGPU kernels, diskformer, kohra) that fits the model's format, architecture and your GPU budget.",
   "type": "module",
   "main": "./index.js",

package/src/backends/transformers.js

@@ -120,16 +120,33 @@ export const transformersBackend = {
     const gen = await lib.pipeline('text-generation', model.repo, {
       device: 'webgpu', dtype, revision: model.revision || 'main', progress_callback,
     });
+    feedLogitsToKeep(lib, gen.model);
     signal?.throwIfAborted();
     return {
       task: 'text-generation',
-      generate: (messages, { maxNewTokens = 256, repetitionPenalty, signal } = {}) => stream(lib, gen.tokenizer, signal,
-        (streamer, stopping_criteria) => gen(messages, { max_new_tokens: maxNewTokens, do_sample: false, ...(repetitionPenalty && { repetition_penalty: repetitionPenalty }), streamer, stopping_criteria })),
+      // thinking: false (the default, as on every back end here) renders the template with enable_thinking off, so a
+      // model that reasons by default (LFM3) answers directly; templates without the switch ignore it.
+      generate: (messages, { maxNewTokens = 256, repetitionPenalty, signal, thinking = false } = {}) => stream(lib, gen.tokenizer, signal,
+        (streamer, stopping_criteria) => gen(messages, { max_new_tokens: maxNewTokens, do_sample: false, ...(repetitionPenalty && { repetition_penalty: repetitionPenalty }), tokenizer_encode_kwargs: { enable_thinking: thinking === true }, streamer, stopping_criteria })),
       dispose: () => gen.dispose?.(),
     };
   },
 };
 
+// LiquidAI's LFM3 ONNX export names its last-position input logits_to_keep (shape [1]); transformers.js 4.3.2 feeds
+// only num_logits_to_keep and stops with "Missing the following inputs: logits_to_keep". Hide the input from
+// transformers.js's check and add it at the session's run, set to 1: generate() reads only the last position's logits.
+// LocalMind carries the same shim (index.html feedLogitsToKeep).
+function feedLogitsToKeep(lib, net) {
+  const sess = net?.sessions?.model;
+  if (!sess?.inputNames.includes('logits_to_keep')) return;
+  const names = sess.inputNames.filter((n) => n !== 'logits_to_keep');
+  const one = new lib.Tensor('int64', [1n], [1]).ort_tensor;
+  const run = sess.run.bind(sess);
+  Object.defineProperty(sess, 'inputNames', { value: names });
+  sess.run = (feeds, opts) => run({ ...feeds, logits_to_keep: one }, opts);
+}
+
 // A non-generation task: one pipeline, run(input, opts) calls it. ImageData (from a canvas) becomes a RawImage; URLs,
 // RawImage and, for speech, 16 kHz Float32Array samples pass through as transformers.js takes them.
 async function loadPipeline(lib, model, task, { progress_callback, signal }) {

package/src/models.js

@@ -20,6 +20,7 @@ const MINICPM5_2B = M('openbmb/MiniCPM5-2B-GGUF', 'wllama', 'text-generation', '
 const QWEN3_0_6B_MDLM = M('naklitechie/Qwen3-0.6B-diffusion-mdlm-ONNX', 'kohra', 'text-generation', 'kohra', { downloadBytes: 1.54e9, diffusion: true });
 const NEMOTRON_DIFFUSION_3B = M('naklitechie/Nemotron-Labs-Diffusion-3B-ONNX', 'kohra', 'text-generation', 'kohra', { downloadBytes: 2.77e9, diffusion: true, experimental: true });
 const GEMMA4_26B_A4B = M('google/gemma-4-26B-A4B-it-qat-q4_0-gguf', 'diskformer', 'text-generation', 'diskformer-chat', { budget: 2.5e9, downloadBytes: 14.44e9 });
+const LFM3_1_7B = M('LiquidAI/LFM3-1.7B-ONNX', 'transformers', 'text-generation', 'chat', { downloadBytes: 1.63e9 });
 const NEMOTRON_3_5_BOLT_E4B = M('danyalmalik/NVIDIA-Nemotron-3.5-Bolt-E4B-ONNX-WebGPU', 'transformers', 'text-generation', 'transformers', { budget: 5e9, downloadBytes: 4.94e9 });
 // A tech demo, not a gated model: 231 GB on disk (4 IQ1_M parts plus the 110.6 GB Engram side file), about 0.4 tok/s.
 // diskformer checked one hand-written prompt through complete(); generate() renders the GGUF's chat template, which no
@@ -54,6 +55,8 @@ export const MODELS = {
     GEMMA4_26B_A4B,
     /** NVIDIA's Nemotron 3.5 Bolt E4B (dense, text only), a community q4f16 ONNX export in Gemma 4 E4B's graph. */
     NEMOTRON_3_5_BOLT_E4B,
+    /** LiquidAI's LFM3 1.7B (dense), LiquidAI's own ONNX export; thinking off unless a request asks for it. */
+    LFM3_1_7B,
     /** DeepSeek V4.1 Flash (763B MoE), a tech demo on diskformer's llama.cpp path: 231 GB on disk, very slow. */
     DEEPSEEK_V4_1_FLASH,
   },

package/src/sources.js

@@ -4,7 +4,7 @@
 // transformers.js and wllama move only by hand, in step with LocalMind's pins (plan/history.md, 2026-10-08).
 
 export const PINS = {
-  transformers: '4.3.1',
+  transformers: '4.3.2', // 4.3.2 adds model_type lfm3 (LFM3 1.7B)
   wllama: '3.4.1',      // LocalMind's pin; its stream-drain workaround (src/backends/wllama.js) is for this version
   // v0.3.1: seeded block-KV graphs (Nemotron-Labs-Diffusion-3B), chatFormat, split external data; download progress
   // (progress_callback) and the graph files cached in Cache Storage 'kohra-models'.