WebGPT
transformers.js
| WebGPT | transformers.js | |
|---|---|---|
| 7 | 26 | |
| 3,516 | 7,587 | |
| - | - | |
| 8.0 | 9.4 | |
| 4 months ago | 2 days ago | |
| JavaScript | JavaScript | |
| GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
WebGPT
- WebGPT: GPT Model on the Browser with WebGPU
- WebGPT: Run GPT model on the browser with WebGPU
- Pinbot – An extension to privately search one's browser history with AI
-
Browser Extension: "Find in Page" all synonyms instead of the exact word.
WebGPT might be a good starting point if anyone's interested: Repo. It basically is a local language model powered by the new WebGPU stuff.
- Run GPT model on the browser with WebGPU
-
WebGPU GPT Model Demo
Question. I can see in the code the WGSL that's needed to implement inference on the GPU. https://github.com/0hq/WebGPT/blob/main/kernels.js
Could this code also be used to train models or only for inference?
What I'm getting at, is could I take the WGSL and using rust wgpu create a mini ChatGPT that runs on all GPU's?
- WebGPT: Run GPT2 on the Browser with WebGPU
transformers.js
-
Transformers.js: Machine Learning for the Web
We have some other WebGPU demos, including:
- WebGPU embedding benchmark: https://huggingface.co/spaces/Xenova/webgpu-embedding-benchm...
- Real-time object detection: https://huggingface.co/spaces/Xenova/webgpu-video-object-det...
- Real-time background removal: https://huggingface.co/spaces/Xenova/webgpu-video-background...
- WebGPU depth estimation: https://huggingface.co/spaces/Xenova/webgpu-depth-anything
- Image background removal: https://huggingface.co/spaces/Xenova/remove-background-webgp...
You can follow the progress for full WebGPU support in the v3 development branch (https://github.com/xenova/transformers.js/pull/545).
To answer your question, while there are certain ops missing, the main limitation at the moment is for models with decoders... which are not very fast (yet) due to inefficient buffer reuse and many redundant copies between CPU and GPU. We're working closely with the ORT team to fix these issues though!
-
Deep Learning in JavaScript
BTW: you might want to add support for typed arrays.
See: https://github.com/xenova/transformers.js/blob/8804c36591d11...
This is really old, but added as part of the shape of the vector as well: https://github.com/nicolaspanel/numjs/blob/master/src/dtypes...
-
Deja-Vu your AI✦ Bookmarking Tool
Made possible by Xenova and Supabase / gte-small
-
Extracting YouTube video data with OpenAI and LangChain
To build the application, you’ll use the youtube-transcript package to retrieve YouTube video transcripts. You will then use LangChain and the Transformers.js package to generate free Hugging Face embeddings for the given transcript and store them in a vector store instead of relying on potentially expensive OpenAI embeddings. Lastly, you will use LangChain and an OpenAI model to retrieve information stored in the vector store.
- Transformers.js releases Zero-shot audio classification support
-
How to Use AI/ML Models for Your Projects
Transformers.js: A groundbreaking library, Transformers.js brings transformer models like GPT-3, BERT, and Whisper straight to your browser. With the introduction of technologies like webGPU and LLM, Transformers.js has garnered significant attention. If you’d like to learn how to integrate a small model in the UI, check out their code and examples here.
-
Show HN: Tiny LLMs – Browser-based private AI models for a wide array of tasks
The announcement seems somewhat disingenuous. The PR[1] found from their release notes[2] seems to contain only boilerplate and no real support for Mistral models or their weights.
[1]: https://github.com/xenova/transformers.js/pull/379
- Transformers.js
- Transformers.js: Run Machine Learning models directly in the browser
- What is the most cost-efficient way to have an embedding generator endpoint that is using an open-source embedding model? [Q]
What are some alternatives?
FindSynonyms - Chrome extension that replaces words in web pages with their synonyms.
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
gpt-tfjs - GPT in TensorFlow.js
web-stable-diffusion - Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.
web-llm - Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.
web-ai - Run modern deep learning models in the browser.
three.js - JavaScript 3D Library.
spark-nlp - State of the Art Natural Language Processing
memory64 - Memory with 64-bit indexes
vertex-ai-samples - Sample code and notebooks for Vertex AI, the end-to-end machine learning platform on Google Cloud
openai-java - OpenAI Api Client in Java
tvm - Open deep learning compiler stack for cpu, gpu and specialized accelerators