-
Notifications
You must be signed in to change notification settings - Fork 748
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #985 from huggingface/v3-docs
Improve documentation (v3)
- Loading branch information
Showing
9 changed files
with
332 additions
and
69 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -11,25 +11,19 @@ | |
| </p> | ||
|
|
||
| <p align="center"> | ||
| <a href="https://www.npmjs.com/package/@huggingface/transformers"> | ||
| <img alt="NPM" src="https://img.shields.io/npm/v/@huggingface/transformers"> | ||
| </a> | ||
| <a href="https://www.npmjs.com/package/@huggingface/transformers"> | ||
| <img alt="NPM Downloads" src="https://img.shields.io/npm/dw/@huggingface/transformers"> | ||
| </a> | ||
| <a href="https://www.jsdelivr.com/package/npm/@huggingface/transformers"> | ||
| <img alt="jsDelivr Hits" src="https://img.shields.io/jsdelivr/npm/hw/@huggingface/transformers"> | ||
| </a> | ||
| <a href="https://github.com/huggingface/transformers.js/blob/main/LICENSE"> | ||
| <img alt="License" src="https://img.shields.io/github/license/huggingface/transformers.js?color=blue"> | ||
| </a> | ||
| <a href="https://huggingface.co/docs/transformers.js/index"> | ||
| <img alt="Documentation" src="https://img.shields.io/website/http/huggingface.co/docs/transformers.js/index.svg?down_color=red&down_message=offline&up_message=online"> | ||
| </a> | ||
| <a href="https://www.npmjs.com/package/@huggingface/transformers"><img alt="NPM" src="https://img.shields.io/npm/v/@huggingface/transformers"></a> | ||
| <a href="https://www.npmjs.com/package/@huggingface/transformers"><img alt="NPM Downloads" src="https://img.shields.io/npm/dw/@huggingface/transformers"></a> | ||
| <a href="https://www.jsdelivr.com/package/npm/@huggingface/transformers"><img alt="jsDelivr Hits" src="https://img.shields.io/jsdelivr/npm/hw/@huggingface/transformers"></a> | ||
| <a href="https://github.com/huggingface/transformers.js/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/github/license/huggingface/transformers.js?color=blue"></a> | ||
| <a href="https://huggingface.co/docs/transformers.js/index"><img alt="Documentation" src="https://img.shields.io/website/http/huggingface.co/docs/transformers.js/index.svg?down_color=red&down_message=offline&up_message=online"></a> | ||
| </p> | ||
|
|
||
|
|
||
| State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server! | ||
| <h3 align="center"> | ||
| <p>State-of-the-art Machine Learning for the Web</p> | ||
| </h3> | ||
|
|
||
| Run 🤗 Transformers directly in your browser, with no need for a server! | ||
|
|
||
| Transformers.js is designed to be functionally equivalent to Hugging Face's [transformers](https://github.com/huggingface/transformers) python library, meaning you can run the same pretrained models using a very similar API. These models support common tasks in different modalities, such as: | ||
| - 📝 **Natural Language Processing**: text classification, named entity recognition, question answering, language modeling, summarization, translation, multiple choice, and text generation. | ||
|
|
@@ -42,6 +36,22 @@ Transformers.js uses [ONNX Runtime](https://onnxruntime.ai/) to run models in th | |
| For more information, check out the full [documentation](https://huggingface.co/docs/transformers.js). | ||
|
|
||
|
|
||
| ## Installation | ||
|
|
||
|
|
||
| To install via [NPM](https://www.npmjs.com/package/@huggingface/transformers), run: | ||
| ```bash | ||
| npm i @huggingface/transformers | ||
| ``` | ||
|
|
||
| Alternatively, you can use it in vanilla JS, without any bundler, by using a CDN or static hosting. For example, using [ES Modules](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Modules), you can import the library with: | ||
| ```html | ||
| <script type="module"> | ||
| import { pipeline } from 'https://cdn.jsdelivr.net/npm/@huggingface/[email protected]'; | ||
| </script> | ||
| ``` | ||
|
|
||
|
|
||
| ## Quick tour | ||
|
|
||
|
|
||
|
|
@@ -72,9 +82,9 @@ out = pipe('I love transformers!') | |
| import { pipeline } from '@huggingface/transformers'; | ||
|
|
||
| // Allocate a pipeline for sentiment-analysis | ||
| let pipe = await pipeline('sentiment-analysis'); | ||
| const pipe = await pipeline('sentiment-analysis'); | ||
|
|
||
| let out = await pipe('I love transformers!'); | ||
| const out = await pipe('I love transformers!'); | ||
| // [{'label': 'POSITIVE', 'score': 0.999817686}] | ||
| ``` | ||
|
|
||
|
|
@@ -86,29 +96,40 @@ let out = await pipe('I love transformers!'); | |
| You can also use a different model by specifying the model id or path as the second argument to the `pipeline` function. For example: | ||
| ```javascript | ||
| // Use a different model for sentiment-analysis | ||
| let pipe = await pipeline('sentiment-analysis', 'Xenova/bert-base-multilingual-uncased-sentiment'); | ||
| const pipe = await pipeline('sentiment-analysis', 'Xenova/bert-base-multilingual-uncased-sentiment'); | ||
| ``` | ||
|
|
||
| By default, when running in the browser, the model will be run on your CPU (via WASM). If you would like | ||
| to run the model on your GPU (via WebGPU), you can do this by setting `device: 'webgpu'`, for example: | ||
| ```javascript | ||
| // Run the model on WebGPU | ||
| const pipe = await pipeline('sentiment-analysis', 'Xenova/distilbert-base-uncased-finetuned-sst-2-english', { | ||
| device: 'webgpu', | ||
| }); | ||
| ``` | ||
|
|
||
| ## Installation | ||
| For more information, check out the [WebGPU guide](https://huggingface.co/docs/transformers.js/guides/webgpu). | ||
|
|
||
| > [!WARNING] | ||
| > The WebGPU API is still experimental in many browsers, so if you run into any issues, | ||
| > please file a [bug report](https://github.com/huggingface/transformers.js/issues/new?title=%5BWebGPU%5D%20Error%20running%20MODEL_ID_GOES_HERE&assignees=&labels=bug,webgpu&projects=&template=1_bug-report.yml). | ||
| To install via [NPM](https://www.npmjs.com/package/@huggingface/transformers), run: | ||
| ```bash | ||
| npm i @huggingface/transformers | ||
| ``` | ||
|
|
||
| Alternatively, you can use it in vanilla JS, without any bundler, by using a CDN or static hosting. For example, using [ES Modules](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Modules), you can import the library with: | ||
| ```html | ||
| <script type="module"> | ||
| import { pipeline } from 'https://cdn.jsdelivr.net/npm/@huggingface/[email protected]'; | ||
| </script> | ||
| In resource-constrained environments, such as web browsers, it is advisable to use a quantized version of | ||
| the model to lower bandwidth and optimize performance. This can be achieved by adjusting the `dtype` option, | ||
| which allows you to select the appropriate data type for your model. While the available options may vary | ||
| depending on the specific model, typical choices include `"fp32"` (default for WebGPU), `"fp16"`, `"q8"` | ||
| (default for WASM), and `"q4"`. For more information, check out the [quantization guide](https://huggingface.co/docs/transformers.js/guides/dtypes). | ||
| ```javascript | ||
| // Run the model at 4-bit quantization | ||
| const pipe = await pipeline('sentiment-analysis', 'Xenova/distilbert-base-uncased-finetuned-sst-2-english', { | ||
| dtype: 'q4', | ||
| }); | ||
| ``` | ||
|
|
||
|
|
||
| ## Examples | ||
|
|
||
| Want to jump straight in? Get started with one of our sample applications/templates: | ||
| Want to jump straight in? Get started with one of our sample applications/templates, which can be found [here](https://github.com/huggingface/transformers.js-examples). | ||
|
|
||
| | Name | Description | Links | | ||
| |-------------------|----------------------------------|-------------------------------| | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,130 @@ | ||
| # Using quantized models (dtypes) | ||
|
|
||
| Before Transformers.js v3, we used the `quantized` option to specify whether to use a quantized (q8) or full-precision (fp32) variant of the model by setting `quantized` to `true` or `false`, respectively. Now, we've added the ability to select from a much larger list with the `dtype` parameter. | ||
|
|
||
| The list of available quantizations depends on the model, but some common ones are: full-precision (`"fp32"`), half-precision (`"fp16"`), 8-bit (`"q8"`, `"int8"`, `"uint8"`), and 4-bit (`"q4"`, `"bnb4"`, `"q4f16"`). | ||
|
|
||
| <p align="center"> | ||
| <picture> | ||
| <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/transformersjs-v3/dtypes-dark.jpg" style="max-width: 100%;"> | ||
| <source media="(prefers-color-scheme: light)" srcset="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/transformersjs-v3/dtypes-light.jpg" style="max-width: 100%;"> | ||
| <img alt="Available dtypes for mixedbread-ai/mxbai-embed-xsmall-v1" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/transformersjs-v3/dtypes-dark.jpg" style="max-width: 100%;"> | ||
| </picture> | ||
| <a href="https://huggingface.co/mixedbread-ai/mxbai-embed-xsmall-v1/tree/main/onnx">(e.g., mixedbread-ai/mxbai-embed-xsmall-v1)</a> | ||
| </p> | ||
|
|
||
| ## Basic usage | ||
|
|
||
| **Example:** Run Qwen2.5-0.5B-Instruct in 4-bit quantization ([demo](https://v2.scrimba.com/s0dlcpv0ci)) | ||
|
|
||
| ```js | ||
| import { pipeline } from "@huggingface/transformers"; | ||
|
|
||
| // Create a text generation pipeline | ||
| const generator = await pipeline( | ||
| "text-generation", | ||
| "onnx-community/Qwen2.5-0.5B-Instruct", | ||
| { dtype: "q4", device: "webgpu" }, | ||
| ); | ||
|
|
||
| // Define the list of messages | ||
| const messages = [ | ||
| { role: "system", content: "You are a helpful assistant." }, | ||
| { role: "user", content: "Tell me a funny joke." }, | ||
| ]; | ||
|
|
||
| // Generate a response | ||
| const output = await generator(messages, { max_new_tokens: 128 }); | ||
| console.log(output[0].generated_text.at(-1).content); | ||
| ``` | ||
|
|
||
| ## Per-module dtypes | ||
|
|
||
| Some encoder-decoder models, like Whisper or Florence-2, are extremely sensitive to quantization settings: especially of the encoder. For this reason, we added the ability to select per-module dtypes, which can be done by providing a mapping from module name to dtype. | ||
|
|
||
| **Example:** Run Florence-2 on WebGPU ([demo](https://v2.scrimba.com/s0pdm485fo)) | ||
|
|
||
| ```js | ||
| import { Florence2ForConditionalGeneration } from "@huggingface/transformers"; | ||
|
|
||
| const model = await Florence2ForConditionalGeneration.from_pretrained( | ||
| "onnx-community/Florence-2-base-ft", | ||
| { | ||
| dtype: { | ||
| embed_tokens: "fp16", | ||
| vision_encoder: "fp16", | ||
| encoder_model: "q4", | ||
| decoder_model_merged: "q4", | ||
| }, | ||
| device: "webgpu", | ||
| }, | ||
| ); | ||
| ``` | ||
|
|
||
| <p align="middle"> | ||
| <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/transformersjs-v3/florence-2-webgpu.gif" alt="Florence-2 running on WebGPU" /> | ||
| </p> | ||
|
|
||
| <details> | ||
| <summary> | ||
| See full code example | ||
| </summary> | ||
|
|
||
| ```js | ||
| import { | ||
| Florence2ForConditionalGeneration, | ||
| AutoProcessor, | ||
| AutoTokenizer, | ||
| RawImage, | ||
| } from "@huggingface/transformers"; | ||
|
|
||
| // Load model, processor, and tokenizer | ||
| const model_id = "onnx-community/Florence-2-base-ft"; | ||
| const model = await Florence2ForConditionalGeneration.from_pretrained( | ||
| model_id, | ||
| { | ||
| dtype: { | ||
| embed_tokens: "fp16", | ||
| vision_encoder: "fp16", | ||
| encoder_model: "q4", | ||
| decoder_model_merged: "q4", | ||
| }, | ||
| device: "webgpu", | ||
| }, | ||
| ); | ||
| const processor = await AutoProcessor.from_pretrained(model_id); | ||
| const tokenizer = await AutoTokenizer.from_pretrained(model_id); | ||
|
|
||
| // Load image and prepare vision inputs | ||
| const url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"; | ||
| const image = await RawImage.fromURL(url); | ||
| const vision_inputs = await processor(image); | ||
|
|
||
| // Specify task and prepare text inputs | ||
| const task = "<MORE_DETAILED_CAPTION>"; | ||
| const prompts = processor.construct_prompts(task); | ||
| const text_inputs = tokenizer(prompts); | ||
|
|
||
| // Generate text | ||
| const generated_ids = await model.generate({ | ||
| ...text_inputs, | ||
| ...vision_inputs, | ||
| max_new_tokens: 100, | ||
| }); | ||
|
|
||
| // Decode generated text | ||
| const generated_text = tokenizer.batch_decode(generated_ids, { | ||
| skip_special_tokens: false, | ||
| })[0]; | ||
|
|
||
| // Post-process the generated text | ||
| const result = processor.post_process_generation( | ||
| generated_text, | ||
| task, | ||
| image.size, | ||
| ); | ||
| console.log(result); | ||
| // { '<MORE_DETAILED_CAPTION>': 'A green car is parked in front of a tan building. The building has a brown door and two brown windows. The car is a two door and the door is closed. The green car has black tires.' } | ||
| ``` | ||
|
|
||
| </details> |
Oops, something went wrong.