lxe / wasm-gptLinks
Tensor library for machine learning
☆275Updated 2 years ago
Alternatives and similar repositories for wasm-gpt
Users that are interested in wasm-gpt are comparing it to the libraries listed below
Sorting:
- OpenAI-compatible Python client that can call any LLM☆371Updated 2 years ago
- Add local LLMs to your Web or Electron apps! Powered by Rust + WebGPU☆102Updated last year
- ☆145Updated last year
- WebGPU LLM inference tuned by hand☆150Updated last year
- TypeScript generator for llama.cpp Grammar directly from TypeScript interfaces☆137Updated 10 months ago
- JS tokenizer for LLaMA 1 and 2☆350Updated 11 months ago
- Revealing example of self-attention, the building block of transformer AI models☆130Updated 2 years ago
- Enforce structured output from LLMs 100% of the time☆249Updated 10 months ago
- Extend the original llama.cpp repo to support redpajama model.☆117Updated 9 months ago
- Browser-compatible JS library for running language models☆228Updated 2 years ago
- An implementation of bucketMul LLM inference☆217Updated 11 months ago
- ☆163Updated last year
- LLM-based tool for parsing information and chatting with it☆214Updated last year
- LLaMa retrieval plugin script using OpenAI's retrieval plugin☆323Updated 2 years ago
- Run GGML models with Kubernetes.☆172Updated last year
- 🦜️🔗 This is a very simple re-implementation of LangChain, in ~100 lines of code☆253Updated last year
- C++ implementation for BLOOM☆809Updated 2 years ago
- Layered, depth-first reading—start with summaries, tap to explore details, and gain clarity on complex topics.☆271Updated last year
- ☆252Updated last year
- A tiny implementation of an autonomous agent powered by LLMs (OpenAI GPT-4)☆442Updated 2 years ago
- Applied methods of analytical augmentation to build tools using large-language models.☆26Updated 2 years ago
- Augment GPT-4 Environment Access☆284Updated 2 years ago
- Transformer neural networks in the browser☆91Updated 2 years ago
- ☆143Updated 2 years ago
- https://ermine.ai -- 100% client-side live audio transcription, powered by transformers.js☆325Updated 2 years ago
- Easy-to-use headless React Hooks to run LLMs in the browser with WebGPU. Just useLLM().☆692Updated last year
- Finetune llama2-70b and codellama on MacBook Air without quantization☆447Updated last year
- A library for incremental loading of large PyTorch checkpoints☆56Updated 2 years ago
- Redteaming LLMs using other LLMs☆252Updated 2 years ago
- Simple embedding -> text model trained on a small subset of Wikipedia sentences.☆151Updated last year