mingwu2333
Follow
Stars
Let ChatGPT teach your own chatbot in hours with a single GPU!
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
Advanced Multi-Turn QA System with LLM and Intent Recognition. 基于LLM大语言模型意图识别、参数抽取结合slot词槽技术实现多轮问答、NL2API. 打造Function Call多轮问答最佳实践
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
Firefly: 大模型训练工具，支持训练Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
An open source library for deep learning end-to-end dialog systems and chatbots.
本项目是针对RAG中的Retrieve阶段的召回技术及算法效果所做评估实验。使用主体框架为LlamaIndex.
💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
A tutorial and implement of disease centered Medical knowledge graph and qa system based on it。知识图谱构建，自动问答，基于kg的自动问答。以疾病为中心的一定规模医药领域知识图谱，并以该知识图谱完成自动问答与分析服务。
RAGOnMedicalKG，将大模型RAG与KG结合，完成demo级问答，旨在给出基础的思路。
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
"Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases" by Jiarui Li and Ye Yuan and Zehua Zhang
Superfast AI decision making and intelligent processing of multi-modal data.
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.
Large-scale Pre-training Corpus for Chinese 100G 中文预训练语料
An LLM-powered advanced RAG pipeline built from scratch
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…
[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models
A modular RL library to fine-tune language models to human preferences
HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels