Repository navigation
chatglm3
- Website
- Wikipedia
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
欢迎star⭐。🚀从聊天记录创造数字分身的一站式解决方案💡 使用微信聊天记录微调大语言模型,使用微信语音消息➕0.5B大模型实现高质量声音克隆,并绑定到聊天机器人,实现自己的数字分身。 数字克隆/数字分身/数字永生/声音克隆/LLM/大语言模型/微信聊天机器人/LoRA
LLM API Server , OpenAI 同时支持 ChatGLM3 ,Llama, Llama-3, Firefunction, Openfunctions ,BAAI/bge-m3 ,bge-large-zh-v1.5
A Genshin Impact Book Question Answer Project supported by LLM
Deploy a demo of ChatGLM3 using Docker, Docker Compose, and Poetry in an environment without a GPU.
Genshin Impact Character Instruction Models tuned by Lora on LLM
This project accelerates local deployment of chatglm and vector inference using PyTorch compiled in C++, and includes an OpenAI API Mock script for quick setup of local speed testing services. This setup enhances performance and efficiency, ideal for high-performance applications and development testing.
一个小玩具demo:使用LangChain调用本地ChatGLM3-6B模型实现的搜索引擎agent
Popular Large Language Model's modeling file and finetune+pretrain scripts, including: llama, grok, chatglm2+3, glm, qwen, qwen2, gpt2, mistral, ...