EvilPsyCHo/Play-with-LLMs

Tutorial on training, evaluating LLM, as well as utilizing RAG, Agent, Chain to build entertaining applications with LLMs.分享如何训练、评估LLMs，如何基于RAG、Agent、Chain构建有趣的LLMs应用。

🔥Play with LLMs

分享如何训练、评估大型语言模型，基于RAG、Agent、Chain构建有趣的LLMs应用。

🚀上手即用｜ I code this so you don't have to!

• Mistral-8x7b-Instruct 稳定输出Json Format, 搭配Llamacpp grammar
• Mistral-8x7b-Instruct CoT Agent, Think step by steps
• Mistral-8x7b-Instruct ReAct Agent with tool call
• Llama3-8b-Instruct, transformers, vLLM and Llamacpp多种方法调戏
• Llama3-8b-Instruct, CoT with vLLM
• Llama3-8b-Instruct, 纯中文实现ReAct with tool call
• Chinese-Llama3-8b, DPO微调让Llama3更愿意说中文
• llama-cpp-convert-GGUF, 模型量化转化为GGUF格式并上传huggingface
• Advanced ReAct

🐬深入LLMs | Pretraining, Fine-tuning, RLHF and ?>

• qlora-finetune-Baichuan-7B

案例展示

Mixtral 8x7b ReAct	Llama3-8b ReAct