OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXiu-貔貅 means fortune.

EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit

An Experiment on Dynamic NTK Scaling RoPE

A pytorch implementaion of physics informed neural networks for two dimensional NS equation

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型

LexiLaw - 中文法律大模型

Law Crime Mining Based on Corpus build and content analysis by NLP methods. 基于领域语料库构建与NLP方法的裁判文书与犯罪案例文本挖掘项目

Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型

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

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Llama from scratch, or How to implement a paper without crying

A Simplified PyTorch Implementation of Vision Transformer (ViT)

欢迎来到 LLM-Dojo，这里是一个开源大模型学习场所(最好的学习永远在项目中)，包括一个开源大模型训练框架，以及llm_tricks模块，其中包括各种大模型的tricks实现与原理讲解！。👩‍🎓👨‍🎓

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

Official inference library for Mistral models

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

LLM training code for Databricks foundation models

Examples in the MLX framework

Examples and guides for using the GLM APIs

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

实现了Baichuan-Chat微调，Lora、QLora等各种微调方式，一键运行。

the newest version of llama3，source code explained line by line using Chinese

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.

[NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other models

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Code and documentation to train Stanford's Alpaca models, and generate the data.

Crawl a site to generate knowledge files to create your own custom GPT from a URL

DeepSeek Coder: Let the Code Write Itself

Do Leetcode exercises in IDE, support leetcode.com and leetcode-cn.com, to meet the basic needs of doing exercises.Support theoretically: IntelliJ IDEA PhpStorm WebStorm PyCharm RubyMine AppCode CL…