kayvr / token-hawkLinks
WebGPU LLM inference tuned by hand
☆150Updated 2 years ago
Alternatives and similar repositories for token-hawk
Users that are interested in token-hawk are comparing it to the libraries listed below
Sorting:
- Full finetuning of large language models without large memory requirements☆93Updated last month
- Extend the original llama.cpp repo to support redpajama model.☆118Updated last year
- LLaVA server (llama.cpp).☆183Updated 2 years ago
- Command-line script for inferencing from models such as MPT-7B-Chat☆99Updated 2 years ago
- An implementation of bucketMul LLM inference☆223Updated last year
- SoTA Transformers with C-backend for fast inference on your CPU.☆308Updated last year
- LLM-based code completion engine☆190Updated 9 months ago
- Command-line script for inferencing from models such as falcon-7b-instruct☆74Updated 2 years ago
- TypeScript generator for llama.cpp Grammar directly from TypeScript interfaces☆140Updated last year
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆123Updated 2 years ago
- Falcon LLM ggml framework with CPU and GPU support☆247Updated last year
- Embeddings focused small version of Llama NLP model☆105Updated 2 years ago
- Tensor library for machine learning☆273Updated 2 years ago
- Run GGML models with Kubernetes.☆174Updated last year
- Add local LLMs to your Web or Electron apps! Powered by Rust + WebGPU☆104Updated 2 years ago
- Mistral7B playing DOOM☆138Updated last year
- ☆40Updated 2 years ago
- ☆112Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- Run inference on replit-3B code instruct model using CPU☆159Updated 2 years ago
- JS tokenizer for LLaMA 1 and 2☆360Updated last year
- Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.☆70Updated 2 years ago
- Generates grammer files from typescript for LLM generation☆38Updated last year
- Drop in replacement for OpenAI, but with Open models.☆153Updated 2 years ago
- Cerule - A Tiny Mighty Vision Model☆67Updated last year
- Stop messing around with finicky sampling parameters and just use DRµGS!☆358Updated last year
- iterate quickly with llama.cpp hot reloading. use the llama.cpp bindings with bun.sh☆50Updated 2 years ago
- GPU accelerated client-side embeddings for vector search, RAG etc.☆65Updated last year
- The GeoV model is a large langauge model designed by Georges Harik and uses Rotary Positional Embeddings with Relative distances (RoPER).…☆121Updated 2 years ago
- Automated prompting and scoring framework to evaluate LLMs using updated human knowledge prompts☆108Updated 2 years ago