Stars
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow
Build and run agents you can see, understand and trust.
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
聚宝盆(Cornucopia): 中文金融系列开源可商用大模型，并提供一套高效轻量化的垂直领域LLM训练框架(Pretraining、SFT、RLHF、Quantize等)
A Next-Generation Training Engine Built for Ultra-Large MoE Models
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。
【LLMs九层妖塔】分享 LLMs在自然语言处理（ChatGLM、Chinese-LLaMA-Alpaca、小羊驼 Vicuna、LLaMA、GPT4ALL等）、信息检索（langchain）、语言合成、语言识别、多模态等领域（Stable Diffusion、MiniGPT-4、VisualGLM-6B、Ziya-Visual等）等 实战与经验。
手把手撕LeetCode题目，扒各种算法套路的裤子。English version supported! Crack LeetCode, not only how, but also why.
TigerBot: A multi-language multi-task LLM
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
HL0718 / baize-chatbot
Forked from project-baize/baize-chatbotLet ChatGPT teach your own chatbot in hours with a single GPU!
Instruct-tune LLaMA on consumer hardware
骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技
CamelBell（驼铃) is be a Chinese Language Tuning project based on LoRA. CamelBell is belongs to Project Luotuo(骆驼), an open sourced Chinese-LLM project created by 冷子昂 @ 商汤科技 & 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技
Python - 100天从新手到大师
WhiteFu / pycorrector
Forked from shibing624/pycorrectorpycorrector is a toolkit for text error correction. 文本纠错，Kenlm，Seq2Seq_Attention，BERT，MacBERT，ELECTRA，ERNIE，Transformer等模型实现，开箱即用。
此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。