ligang's repositories
AppAgent
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
Awesome-Chinese-LLM
整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。
baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
ChatGLM-Finetuning
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
ChatPDF
RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF
crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
DB-GPT
AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents
deploy
Pandora Cloud + Pandora Server + Shared Chat + BackendAPI Proxy + Chat2API + Signup Free = PandoraNext. New GPTs(Gizmo) UI, All in one!
gpt-researcher
GPT based autonomous agent that does online comprehensive research on any given topic
GPT_API_free
Free ChatGPT API Key,免费ChatGPT API,支持GPT4 API(免费),ChatGPT国内可用免费转发API,直连无需代理。可以搭配ChatBox等软件/插件使用,极大降低接口使用成本。国内即可无限制畅快聊天。
LLaMA-Factory
Unify Efficient Fine-Tuning of 100+ LLMs
llama_index
LlamaIndex (formerly GPT Index) is a data framework for your LLM applications
llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
LLM-quickstart
Quick Start for Large Language Models (Theoretical Learning and Practical Fine-tuning) 大语言模型快速入门(理论学习与微调实战)
llm_interview_note
主要记录大语言大模型(LLMs) 算法(应用)工程师相关的知识及面试题
MedicalGPT
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、有监督微调、RLHF(奖励建模、强化学习训练)和DPO(直接偏好优化)。
MINI_LLM
This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.
nlp_chinese_corpus
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
numpy-ml
Machine learning, in numpy
open-webui
User-friendly WebUI for LLMs (Formerly Ollama WebUI)
privateGPT
Interact with your documents using the power of GPT, 100% privately, no data leaks
python-mini-project
🙌 Welcome open-source Python mini-project contributions!
pytorch-model-train-template
pytorch单精度、半精度、混合精度、单卡、多卡(DP / DDP)、FSDP、DeepSpeed模型训练代码,并对比不同方法的训练速度以及GPU内存的使用
self-rag
This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.
simple_RAG_with_LLMs_API
基于大语言模型API(本地或商用API)的外挂知识库问答系统(附neo4j实现知识图谱)
trl
Train transformer language models with reinforcement learning.