https://github.com/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。
https://github.com/evilpsycho/play-with-llms

agent baichuan2 chatgpt gpt large-language-models llama2 llms mistral rag retrieval-augmented-generation

Last synced: about 2 months ago
JSON representation

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。

• Host: GitHub
• URL: https://github.com/evilpsycho/play-with-llms
• Owner: EvilPsyCHo
• License: mit
• Created: 2023-06-24T14:05:41.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-05-02T08:51:23.000Z (5 months ago)
• Last Synced: 2024-08-01T04:04:05.827Z (about 2 months ago)
• Topics: agent, baichuan2, chatgpt, gpt, large-language-models, llama2, llms, mistral, rag, retrieval-augmented-generation
• Language: Jupyter Notebook
• Homepage: https://kky42.com/
• Size: 1.3 MB
• Stars: 481
• Watchers: 7
• Forks: 80
• Open Issues: 14
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-ChatGPT-repositories - 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。 (Tutorials)

README

        



🔥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](./examples/mistral-stable-output-JSON-format.ipynb)

- [Mistral-8x7b-Instruct CoT Agent, Think step by steps](./examples/mistral-CoT-Agent.ipynb)

- [Mistral-8x7b-Instruct ReAct Agent with tool call](./examples/mistral-ReAct-Agent-with-function-tool-call.ipynb)

- [Llama3-8b-Instruct, transformers, vLLM and Llamacpp多种方法调戏](./examples/llama3-8b-Instruct-transformers-vllm-llamacpp.ipynb)

- [Llama3-8b-Instruct, CoT with vLLM](./examples/llama3-8b-Instruct-CoT-Agent-vllm.ipynb)

- [Llama3-8b-Instruct, 纯中文实现ReAct with tool call](./examples/llama3-8b-Instruct-CoT-Agent-vllm.ipynb)

- [Chinese-Llama3-8b, DPO微调让Llama3更愿意说中文](./examples/chinese-llama3-8b.ipynb)

- [llama-cpp-convert-GGUF, 模型量化转化为GGUF格式并上传huggingface](./examples/llama-cpp-convert-GGUF.ipynb)

- [Advanced ReAct](./examples/llama3-8b-Instruct-ReAct-Agent-advanced.ipynb)

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

- [qlora-finetune-Baichuan-7B](./finetune-qlora-baichuan/README.md)

### 案例展示

Mixtral 8x7b ReAct           |  Llama3-8b ReAct

:-------------------------:|:-------------------------:

![](./assets/simple-react.gif)  |  ![](./assets/llama3_simple_react.gif)