s1: Simple test-time scaling

A series of math-specific large language models of our Qwen2 series.

A framework for few-shot evaluation of autoregressive language models.

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention)

Fast and memory-efficient exact attention

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Ring attention implementation with flash attention

Solve puzzles. Learn CUDA.

Code for Quiet-STaR

A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

🛏 An HTML to Markdown converter written in JavaScript

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

Open deep learning compiler stack for cpu, gpu and specialized accelerators

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨

本项目是一个通过文字生成图片的项目，基于开源模型Stable Diffusion V1.5生成可以在手机的CPU和NPU上运行的模型，包括其配套的模型运行框架。

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Preprint: Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Learn CUDA Programming, published by Packt

MLX: An array framework for Apple silicon

中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。