@blank-utils/llm 0.5.3 → 0.5.5

package/README.md

@@ -326,18 +326,18 @@ Conditional rendering components:
 
 ### Default Chat Interface explained
 
-The `<Chat>` and `<ChatApp>` components provide a production-ready interface with "Terminal Luxury" aesthetics.
+The `<Chat>` and `<ChatApp>` components provide a production-ready, minimalist, borderless "Terminal" interface inspired by brutalist and sacred computer aesthetics.
 
 **Key Features & Usage Points:**
 
-- **✨ Zero Config**: Just drop it in. No CSS files to import, no state to manage.
+- **✨ Zero Config**: Just drop it in. No CSS files to import, no state to manage. All spacing, monospace typography, and layout are handled out-of-the-box.
 - **🎨 Rich Text Rendering**:
   - **Global Markdown**: Bold, cursives, lists, tables.
-  - **Code Blocks**: Syntax highlighting for 20+ languages.
+  - **Code Blocks**: Syntax highlighting for 20+ languages cleanly integrated without borders.
   - **Diagrams**: Renders `mermaid` diagrams automatically.
   - **Math**: Supports LateX expressions.
 - **⚡ Eager Interaction**: Users can type and send messages _while_ the model is still initializing. The chat controls the queue.
-- **🌗 Theming**: Built-in 'dark' (cherry red accents) and 'light' modes.
+- **🌗 Multimodal & Files**: Deeply integrated multimodal chat input. Simply drag and drop PDFs for automatic local text extraction, or drag-and-drop/paste images for seamless processing against vision models (e.g., `phi-3.5-vision`). WebLLM crash mitigations for dynamic image cropping are automatically handled.
 - **🔄 Model Switching**:
   - If using `<ChatApp />`, a model selector dropdown is included automatically.
   - If using `<Chat />`, pass `onModelChange` to enable the dropdown.
@@ -497,32 +497,19 @@ You can use either the **alias** (short name) or the **full model ID** when spec
 
 ### WebLLM Backend (WebGPU)
 
-| Alias                   | Model                        | Notes                       |
-| ----------------------- | ---------------------------- | --------------------------- |
-| `llama-3.2-1b`          | Llama 3.2 1B Instruct        | Compact, great quality      |
-| `llama-3.2-3b`          | Llama 3.2 3B Instruct        | Balanced                    |
-| `llama-3.1-8b`          | Llama 3.1 8B Instruct        | High quality                |
-| `llama-3.1-8b-1k`       | Llama 3.1 8B (1K ctx)        | Lower memory                |
-| `phi-3.5-mini`          | Phi 3.5 Mini Instruct        | **Default** — great balance |
-| `phi-3.5-mini-1k`       | Phi 3.5 Mini (1K ctx)        | Lower memory                |
-| `phi-3.5-vision`        | Phi 3.5 Vision               | Vision model                |
-| `qwen-2.5-0.5b`         | Qwen 2.5 0.5B                | Tiny, fast                  |
-| `qwen-2.5-1.5b`         | Qwen 2.5 1.5B                | Small                       |
-| `qwen-2.5-3b`           | Qwen 2.5 3B                  | Medium                      |
-| `qwen-2.5-7b`           | Qwen 2.5 7B                  | Large                       |
-| `qwen-2.5-coder-0.5b`   | Qwen 2.5 Coder 0.5B          | Code-focused                |
-| `qwen-2.5-coder-1.5b`   | Qwen 2.5 Coder 1.5B          | Code-focused                |
-| `gemma-2-2b`            | Gemma 2 2B                   | Google, efficient           |
-| `gemma-2-2b-1k`         | Gemma 2 2B (1K ctx)          | Lower memory                |
-| `gemma-2-9b`            | Gemma 2 9B                   | Large                       |
-| `smollm2-135m`          | SmolLM2 135M                 | Ultra lightweight           |
-| `smollm2-360m`          | SmolLM2 360M                 | Lightweight                 |
-| `smollm2-1.7b`          | SmolLM2 1.7B                 | Small                       |
-| `mistral-7b`            | Mistral 7B v0.3              | General purpose             |
-| `deepseek-r1-qwen-7b`   | DeepSeek R1 Distill Qwen 7B  | Reasoning                   |
-| `deepseek-r1-llama-8b`  | DeepSeek R1 Distill Llama 8B | Reasoning                   |
-| `hermes-3-llama-3.2-3b` | Hermes 3 Llama 3.2 3B        | Function calling            |
-| `hermes-3-llama-3.1-8b` | Hermes 3 Llama 3.1 8B        | Function calling            |
+The WebLLM backend supports **over 80+ WebGPU-accelerated models**, organized into major ecosystems. All models are strongly typed and natively supported:
+
+- **Microsoft Phi**: `phi-3.5-mini`, `phi-3.5-vision` (Multimodal support!), `phi-3-mini-4k`, `phi-2`, `phi-1.5`
+- **Meta Llama**: `llama-3.2-1b`/`3b`, `llama-3.1-8b`/`70b`, `llama-3-8b`/`70b`, `llama-2-7b`/`13b`
+- **Alibaba Qwen**: `qwen3` (`0.6b` to `8b`), `qwen-2.5` (`0.5b` to `7b`), `qwen-2.5-coder` (`0.5b` to `7b`), `qwen-2.5-math` (`1.5b`)
+- **Google Gemma**: `gemma-2-2b`, `gemma-2-9b`, `gemma-2-2b-jpn`, `gemma-2b`
+- **HuggingFace SmolLM2**: `smollm2-135m` (~360MB VRAM!), `smollm2-360m`, `smollm2-1.7b`
+- **Mistral & Ministral**: `mistral-7b` (v0.2/v0.3), `ministral-3-3b-base`/`reasoning`/`instruct`
+- **DeepSeek Reasoning**: `deepseek-r1-qwen-7b`, `deepseek-r1-llama-8b`
+- **NousResearch Hermes**: `hermes-3-llama-3.2-3b`/`3.1-8b`, `hermes-2-theta/pro-llama`, `hermes-pro/openhermes-mistral`
+- **Other**: `tinyllama-1.1b`, `redpajama-3b`, `stablelm-2-zephyr-1.6b`, `wizardmath-7b`
+
+_Note: Many models have `-1k` variants (e.g. `llama-3.1-8b-1k`) with smaller context windows intentionally configured to require significantly less VRAM on constrained devices._
 
 ### Transformers.js Backend (CPU / WASM)
 

package/dist/{chunk-6EZY4F42.js → chunk-OJCFVVNG.js}

@@ -56,43 +56,86 @@ async function logCapabilities() {
 // src/models.ts
 var DEFAULT_WEBLLM_MODEL = "Phi-3.5-mini-instruct-q4f16_1-MLC";
 var WEBLLM_MODELS = {
-  // === Llama 3.2 Models (Meta) - Excellent quality, reasonable size ===
+  // === Llama 3.2 Models ===
   "llama-3.2-1b": "Llama-3.2-1B-Instruct-q4f16_1-MLC",
   "llama-3.2-3b": "Llama-3.2-3B-Instruct-q4f16_1-MLC",
-  // === Llama 3.1 Models (Meta) - Larger, higher quality ===
+  // === Llama 3.1 & 3 Models ===
   "llama-3.1-8b": "Llama-3.1-8B-Instruct-q4f16_1-MLC",
   "llama-3.1-8b-1k": "Llama-3.1-8B-Instruct-q4f16_1-MLC-1k",
-  // Smaller context for lower memory
-  // === Phi Models (Microsoft) - Great balance of size/quality ===
+  "llama-3.1-70b": "Llama-3.1-70B-Instruct-q3f16_1-MLC",
+  "llama-3-8b": "Llama-3-8B-Instruct-q4f16_1-MLC",
+  "llama-3-8b-1k": "Llama-3-8B-Instruct-q4f16_1-MLC-1k",
+  "llama-3-70b": "Llama-3-70B-Instruct-q3f16_1-MLC",
+  // === Llama 2 Models ===
+  "llama-2-7b": "Llama-2-7b-chat-hf-q4f16_1-MLC",
+  "llama-2-7b-1k": "Llama-2-7b-chat-hf-q4f16_1-MLC-1k",
+  "llama-2-13b": "Llama-2-13b-chat-hf-q4f16_1-MLC",
+  // === Phi Models ===
   "phi-3.5-mini": "Phi-3.5-mini-instruct-q4f16_1-MLC",
   "phi-3.5-mini-1k": "Phi-3.5-mini-instruct-q4f16_1-MLC-1k",
-  // Smaller context for lower memory
   "phi-3.5-vision": "Phi-3.5-vision-instruct-q4f16_1-MLC",
   // Vision model
-  // === Qwen 2.5 Models (Alibaba) - Good multilingual support ===
+  "phi-3-mini-4k": "Phi-3-mini-4k-instruct-q4f16_1-MLC",
+  "phi-3-mini-4k-1k": "Phi-3-mini-4k-instruct-q4f16_1-MLC-1k",
+  "phi-2": "phi-2-q4f16_1-MLC",
+  "phi-1.5": "phi-1_5-q4f16_1-MLC",
+  // === Qwen 3 Models ===
+  "qwen3-0.6b": "Qwen3-0.6B-q4f16_1-MLC",
+  "qwen3-1.7b": "Qwen3-1.7B-q4f16_1-MLC",
+  "qwen3-4b": "Qwen3-4B-q4f16_1-MLC",
+  "qwen3-8b": "Qwen3-8B-q4f16_1-MLC",
+  // === Qwen 2.5 Models ===
   "qwen-2.5-0.5b": "Qwen2.5-0.5B-Instruct-q4f16_1-MLC",
   "qwen-2.5-1.5b": "Qwen2.5-1.5B-Instruct-q4f16_1-MLC",
   "qwen-2.5-3b": "Qwen2.5-3B-Instruct-q4f16_1-MLC",
   "qwen-2.5-7b": "Qwen2.5-7B-Instruct-q4f16_1-MLC",
   "qwen-2.5-coder-0.5b": "Qwen2.5-Coder-0.5B-Instruct-q4f16_1-MLC",
   "qwen-2.5-coder-1.5b": "Qwen2.5-Coder-1.5B-Instruct-q4f16_1-MLC",
-  // === Gemma 2 Models (Google) - Efficient and capable ===
+  "qwen-2.5-coder-3b": "Qwen2.5-Coder-3B-Instruct-q4f16_1-MLC",
+  "qwen-2.5-coder-7b": "Qwen2.5-Coder-7B-Instruct-q4f16_1-MLC",
+  "qwen-2.5-math-1.5b": "Qwen2.5-Math-1.5B-Instruct-q4f16_1-MLC",
+  // === Qwen 2 Models ===
+  "qwen2-math-1.5b": "Qwen2-Math-1.5B-Instruct-q4f16_1-MLC",
+  "qwen2-math-7b": "Qwen2-Math-7B-Instruct-q4f16_1-MLC",
+  // === Gemma 2 Models ===
   "gemma-2-2b": "gemma-2-2b-it-q4f16_1-MLC",
   "gemma-2-2b-1k": "gemma-2-2b-it-q4f16_1-MLC-1k",
-  // Smaller context for lower memory
   "gemma-2-9b": "gemma-2-9b-it-q4f16_1-MLC",
-  // === SmolLM2 Models (HuggingFace) - Ultra lightweight ===
+  "gemma-2-2b-jpn": "gemma-2-2b-jpn-it-q4f16_1-MLC",
+  // === Gemma 1 Models ===
+  "gemma-2b": "gemma-2b-it-q4f16_1-MLC",
+  "gemma-2b-1k": "gemma-2b-it-q4f16_1-MLC-1k",
+  // === SmolLM2 Models ===
   "smollm2-135m": "SmolLM2-135M-Instruct-q0f16-MLC",
   "smollm2-360m": "SmolLM2-360M-Instruct-q4f16_1-MLC",
   "smollm2-1.7b": "SmolLM2-1.7B-Instruct-q4f16_1-MLC",
-  // === Mistral Models - Good general purpose ===
+  // === Mistral & Ministral Models ===
   "mistral-7b": "Mistral-7B-Instruct-v0.3-q4f16_1-MLC",
-  // === DeepSeek R1 Distill Models - Reasoning focused ===
+  "mistral-7b-v0.2": "Mistral-7B-Instruct-v0.2-q4f16_1-MLC",
+  "ministral-3-3b-base": "Ministral-3-3B-Base-2512-q4f16_1-MLC",
+  "ministral-3-3b-reasoning": "Ministral-3-3B-Reasoning-2512-q4f16_1-MLC",
+  "ministral-3-3b-instruct": "Ministral-3-3B-Instruct-2512-BF16-q4f16_1-MLC",
+  // === DeepSeek R1 Distill Models ===
   "deepseek-r1-qwen-7b": "DeepSeek-R1-Distill-Qwen-7B-q4f16_1-MLC",
   "deepseek-r1-llama-8b": "DeepSeek-R1-Distill-Llama-8B-q4f16_1-MLC",
-  // === Hermes Models - Function calling capable ===
+  // === Hermes Models ===
   "hermes-3-llama-3.2-3b": "Hermes-3-Llama-3.2-3B-q4f16_1-MLC",
-  "hermes-3-llama-3.1-8b": "Hermes-3-Llama-3.1-8B-q4f16_1-MLC"
+  "hermes-3-llama-3.1-8b": "Hermes-3-Llama-3.1-8B-q4f16_1-MLC",
+  "hermes-2-theta-llama-3-8b": "Hermes-2-Theta-Llama-3-8B-q4f16_1-MLC",
+  "hermes-2-pro-llama-3-8b": "Hermes-2-Pro-Llama-3-8B-q4f16_1-MLC",
+  "hermes-2-pro-mistral-7b": "Hermes-2-Pro-Mistral-7B-q4f16_1-MLC",
+  "openhermes-2.5-mistral-7b": "OpenHermes-2.5-Mistral-7B-q4f16_1-MLC",
+  "neuralhermes-2.5-mistral-7b": "NeuralHermes-2.5-Mistral-7B-q4f16_1-MLC",
+  // === Other Models ===
+  "tinyllama-1.1b": "TinyLlama-1.1B-Chat-v1.0-q4f16_1-MLC",
+  "tinyllama-1.1b-1k": "TinyLlama-1.1B-Chat-v1.0-q4f16_1-MLC-1k",
+  "tinyllama-1.1b-v0.4": "TinyLlama-1.1B-Chat-v0.4-q4f16_1-MLC",
+  "tinyllama-1.1b-v0.4-1k": "TinyLlama-1.1B-Chat-v0.4-q4f16_1-MLC-1k",
+  "redpajama-3b": "RedPajama-INCITE-Chat-3B-v1-q4f16_1-MLC",
+  "redpajama-3b-1k": "RedPajama-INCITE-Chat-3B-v1-q4f16_1-MLC-1k",
+  "stablelm-2-zephyr-1.6b": "stablelm-2-zephyr-1_6b-q4f16_1-MLC",
+  "stablelm-2-zephyr-1.6b-1k": "stablelm-2-zephyr-1_6b-q4f16_1-MLC-1k",
+  "wizardmath-7b": "WizardMath-7B-V1.1-q4f16_1-MLC"
 };
 
 // src/backends/webllm.ts

package/dist/{index-DJmiDzY3.d.ts → index-3qtk9myB.d.ts}

@@ -20,26 +20,67 @@ declare const WEBLLM_MODELS: {
     readonly 'llama-3.2-3b': "Llama-3.2-3B-Instruct-q4f16_1-MLC";
     readonly 'llama-3.1-8b': "Llama-3.1-8B-Instruct-q4f16_1-MLC";
     readonly 'llama-3.1-8b-1k': "Llama-3.1-8B-Instruct-q4f16_1-MLC-1k";
+    readonly 'llama-3.1-70b': "Llama-3.1-70B-Instruct-q3f16_1-MLC";
+    readonly 'llama-3-8b': "Llama-3-8B-Instruct-q4f16_1-MLC";
+    readonly 'llama-3-8b-1k': "Llama-3-8B-Instruct-q4f16_1-MLC-1k";
+    readonly 'llama-3-70b': "Llama-3-70B-Instruct-q3f16_1-MLC";
+    readonly 'llama-2-7b': "Llama-2-7b-chat-hf-q4f16_1-MLC";
+    readonly 'llama-2-7b-1k': "Llama-2-7b-chat-hf-q4f16_1-MLC-1k";
+    readonly 'llama-2-13b': "Llama-2-13b-chat-hf-q4f16_1-MLC";
     readonly 'phi-3.5-mini': "Phi-3.5-mini-instruct-q4f16_1-MLC";
     readonly 'phi-3.5-mini-1k': "Phi-3.5-mini-instruct-q4f16_1-MLC-1k";
     readonly 'phi-3.5-vision': "Phi-3.5-vision-instruct-q4f16_1-MLC";
+    readonly 'phi-3-mini-4k': "Phi-3-mini-4k-instruct-q4f16_1-MLC";
+    readonly 'phi-3-mini-4k-1k': "Phi-3-mini-4k-instruct-q4f16_1-MLC-1k";
+    readonly 'phi-2': "phi-2-q4f16_1-MLC";
+    readonly 'phi-1.5': "phi-1_5-q4f16_1-MLC";
+    readonly 'qwen3-0.6b': "Qwen3-0.6B-q4f16_1-MLC";
+    readonly 'qwen3-1.7b': "Qwen3-1.7B-q4f16_1-MLC";
+    readonly 'qwen3-4b': "Qwen3-4B-q4f16_1-MLC";
+    readonly 'qwen3-8b': "Qwen3-8B-q4f16_1-MLC";
     readonly 'qwen-2.5-0.5b': "Qwen2.5-0.5B-Instruct-q4f16_1-MLC";
     readonly 'qwen-2.5-1.5b': "Qwen2.5-1.5B-Instruct-q4f16_1-MLC";
     readonly 'qwen-2.5-3b': "Qwen2.5-3B-Instruct-q4f16_1-MLC";
     readonly 'qwen-2.5-7b': "Qwen2.5-7B-Instruct-q4f16_1-MLC";
     readonly 'qwen-2.5-coder-0.5b': "Qwen2.5-Coder-0.5B-Instruct-q4f16_1-MLC";
     readonly 'qwen-2.5-coder-1.5b': "Qwen2.5-Coder-1.5B-Instruct-q4f16_1-MLC";
+    readonly 'qwen-2.5-coder-3b': "Qwen2.5-Coder-3B-Instruct-q4f16_1-MLC";
+    readonly 'qwen-2.5-coder-7b': "Qwen2.5-Coder-7B-Instruct-q4f16_1-MLC";
+    readonly 'qwen-2.5-math-1.5b': "Qwen2.5-Math-1.5B-Instruct-q4f16_1-MLC";
+    readonly 'qwen2-math-1.5b': "Qwen2-Math-1.5B-Instruct-q4f16_1-MLC";
+    readonly 'qwen2-math-7b': "Qwen2-Math-7B-Instruct-q4f16_1-MLC";
     readonly 'gemma-2-2b': "gemma-2-2b-it-q4f16_1-MLC";
     readonly 'gemma-2-2b-1k': "gemma-2-2b-it-q4f16_1-MLC-1k";
     readonly 'gemma-2-9b': "gemma-2-9b-it-q4f16_1-MLC";
+    readonly 'gemma-2-2b-jpn': "gemma-2-2b-jpn-it-q4f16_1-MLC";
+    readonly 'gemma-2b': "gemma-2b-it-q4f16_1-MLC";
+    readonly 'gemma-2b-1k': "gemma-2b-it-q4f16_1-MLC-1k";
     readonly 'smollm2-135m': "SmolLM2-135M-Instruct-q0f16-MLC";
     readonly 'smollm2-360m': "SmolLM2-360M-Instruct-q4f16_1-MLC";
     readonly 'smollm2-1.7b': "SmolLM2-1.7B-Instruct-q4f16_1-MLC";
     readonly 'mistral-7b': "Mistral-7B-Instruct-v0.3-q4f16_1-MLC";
+    readonly 'mistral-7b-v0.2': "Mistral-7B-Instruct-v0.2-q4f16_1-MLC";
+    readonly 'ministral-3-3b-base': "Ministral-3-3B-Base-2512-q4f16_1-MLC";
+    readonly 'ministral-3-3b-reasoning': "Ministral-3-3B-Reasoning-2512-q4f16_1-MLC";
+    readonly 'ministral-3-3b-instruct': "Ministral-3-3B-Instruct-2512-BF16-q4f16_1-MLC";
     readonly 'deepseek-r1-qwen-7b': "DeepSeek-R1-Distill-Qwen-7B-q4f16_1-MLC";
     readonly 'deepseek-r1-llama-8b': "DeepSeek-R1-Distill-Llama-8B-q4f16_1-MLC";
     readonly 'hermes-3-llama-3.2-3b': "Hermes-3-Llama-3.2-3B-q4f16_1-MLC";
     readonly 'hermes-3-llama-3.1-8b': "Hermes-3-Llama-3.1-8B-q4f16_1-MLC";
+    readonly 'hermes-2-theta-llama-3-8b': "Hermes-2-Theta-Llama-3-8B-q4f16_1-MLC";
+    readonly 'hermes-2-pro-llama-3-8b': "Hermes-2-Pro-Llama-3-8B-q4f16_1-MLC";
+    readonly 'hermes-2-pro-mistral-7b': "Hermes-2-Pro-Mistral-7B-q4f16_1-MLC";
+    readonly 'openhermes-2.5-mistral-7b': "OpenHermes-2.5-Mistral-7B-q4f16_1-MLC";
+    readonly 'neuralhermes-2.5-mistral-7b': "NeuralHermes-2.5-Mistral-7B-q4f16_1-MLC";
+    readonly 'tinyllama-1.1b': "TinyLlama-1.1B-Chat-v1.0-q4f16_1-MLC";
+    readonly 'tinyllama-1.1b-1k': "TinyLlama-1.1B-Chat-v1.0-q4f16_1-MLC-1k";
+    readonly 'tinyllama-1.1b-v0.4': "TinyLlama-1.1B-Chat-v0.4-q4f16_1-MLC";
+    readonly 'tinyllama-1.1b-v0.4-1k': "TinyLlama-1.1B-Chat-v0.4-q4f16_1-MLC-1k";
+    readonly 'redpajama-3b': "RedPajama-INCITE-Chat-3B-v1-q4f16_1-MLC";
+    readonly 'redpajama-3b-1k': "RedPajama-INCITE-Chat-3B-v1-q4f16_1-MLC-1k";
+    readonly 'stablelm-2-zephyr-1.6b': "stablelm-2-zephyr-1_6b-q4f16_1-MLC";
+    readonly 'stablelm-2-zephyr-1.6b-1k': "stablelm-2-zephyr-1_6b-q4f16_1-MLC-1k";
+    readonly 'wizardmath-7b': "WizardMath-7B-V1.1-q4f16_1-MLC";
 };
 type WebLLMModelID = keyof typeof WEBLLM_MODELS;
 /**

package/dist/index.d.ts

@@ -1,5 +1,5 @@
-import { B as BrowserCapabilities, L as LLMProvider, a as Backend, b as LoadProgressCallback, C as ChatMessage, G as GenerateOptions, S as StreamCallback, A as AttachOptions } from './index-DJmiDzY3.js';
-export { c as Chat, d as ChatInput, e as ChatInputProps, f as ChatProps, D as DEFAULT_WEBLLM_MODEL, g as Device, h as LLMConfig, i as LLMContextValue, j as LLMLoading, k as LLMLoadingProps, l as LLMProvider, m as LLMProviderProps, n as LLMReady, o as LLMReadyProps, p as LoadProgress, q as LocalLLM, M as MessageRole, Q as Quantization, U as UseChatOptions, r as UseChatReturn, s as UseCompletionOptions, t as UseCompletionReturn, u as UseStreamOptions, v as UseStreamReturn, W as WEBLLM_MODELS, w as createLLM, w as default, x as isWebGPUSupported, y as useChat, z as useCompletion, E as useLLM, F as useStream } from './index-DJmiDzY3.js';
+import { B as BrowserCapabilities, L as LLMProvider, a as Backend, b as LoadProgressCallback, C as ChatMessage, G as GenerateOptions, S as StreamCallback, A as AttachOptions } from './index-3qtk9myB.js';
+export { c as Chat, d as ChatInput, e as ChatInputProps, f as ChatProps, D as DEFAULT_WEBLLM_MODEL, g as Device, h as LLMConfig, i as LLMContextValue, j as LLMLoading, k as LLMLoadingProps, l as LLMProvider, m as LLMProviderProps, n as LLMReady, o as LLMReadyProps, p as LoadProgress, q as LocalLLM, M as MessageRole, Q as Quantization, U as UseChatOptions, r as UseChatReturn, s as UseCompletionOptions, t as UseCompletionReturn, u as UseStreamOptions, v as UseStreamReturn, W as WEBLLM_MODELS, w as createLLM, w as default, x as isWebGPUSupported, y as useChat, z as useCompletion, E as useLLM, F as useStream } from './index-3qtk9myB.js';
 import 'react/jsx-runtime';
 import 'react';
 

package/dist/index.js

@@ -22,7 +22,7 @@ import {
   useCompletion,
   useLLM,
   useStream
-} from "./chunk-6EZY4F42.js";
+} from "./chunk-OJCFVVNG.js";
 export {
   Chat,
   ChatInput,

package/dist/react/index.d.ts

@@ -1,3 +1,3 @@
-export { c as Chat, H as ChatApp, I as ChatAppProps, d as ChatInput, e as ChatInputProps, f as ChatProps, J as ImageAttachment, i as LLMContextValue, j as LLMLoading, k as LLMLoadingProps, l as LLMProvider, m as LLMProviderProps, n as LLMReady, o as LLMReadyProps, U as UseChatOptions, r as UseChatReturn, s as UseCompletionOptions, t as UseCompletionReturn, u as UseStreamOptions, v as UseStreamReturn, y as useChat, z as useCompletion, E as useLLM, F as useStream } from '../index-DJmiDzY3.js';
+export { c as Chat, H as ChatApp, I as ChatAppProps, d as ChatInput, e as ChatInputProps, f as ChatProps, J as ImageAttachment, i as LLMContextValue, j as LLMLoading, k as LLMLoadingProps, l as LLMProvider, m as LLMProviderProps, n as LLMReady, o as LLMReadyProps, U as UseChatOptions, r as UseChatReturn, s as UseCompletionOptions, t as UseCompletionReturn, u as UseStreamOptions, v as UseStreamReturn, y as useChat, z as useCompletion, E as useLLM, F as useStream } from '../index-3qtk9myB.js';
 import 'react/jsx-runtime';
 import 'react';

package/dist/react/index.js

@@ -9,7 +9,7 @@ import {
   useCompletion,
   useLLM,
   useStream
-} from "../chunk-6EZY4F42.js";
+} from "../chunk-OJCFVVNG.js";
 export {
   Chat,
   ChatApp,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@blank-utils/llm",
-  "version": "0.5.3",
+  "version": "0.5.5",
   "description": "Run LLMs directly in your browser with WebGPU acceleration. Supports React hooks and eager background loading.",
   "type": "module",
   "main": "./dist/index.js",