LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

A high-throughput and memory-efficient inference and serving engine for LLMs

Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Pushes markdown documents from Github to Notion

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

[NeurIPS'24 Oral] HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

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

Resources of deep learning for mathematical reasoning (DL4MATH).

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining (NeurIPS 2024)

PyTorch native post-training library

code for "Hybrid Ordinary-Welsch Function based Robust Matrix Completion for MIMO Radar" accepted by TAES

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

Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, ChatGLM, ChatGLM2, ChatGLM3 etc.…

📋 A list of open LLMs available for commercial use.

The implementation of DeBERTa

GPT-3: Language Models are Few-Shot Learners

TensorFlow code and pre-trained models for BERT

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

The official Meta Llama 3 GitHub site

Inference code for Llama models

简单易懂的LLaMA微调指南。

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied with elaborately-written concise descriptions to help readers g…