ML
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Curated list of useful LLM / Analytics / Datascience resources
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Instruct-tune LLaMA on consumer hardware
Locally run an Instruction-Tuned Chat-Style LLM
Finetuning large language models for GDScript generation.
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
A system for prompted weak supervision. Alfred is a powerful tool that leverages large language models to accelerate data annotation.
Official repository for LongChat and LongEval
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
Landmark Attention: Random-Access Infinite Context Length for Transformers
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
A Rust implementation of OpenAI's Whisper model using the burn framework
Implementation of Nougat Neural Optical Understanding for Academic Documents
Convert PDF to markdown + JSON quickly with high accuracy
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.