🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

ModelScope-Agent: An agent framework connecting models in ModelScope with the world

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder

360zhinao

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

🚀 基于 LLM 大语言模型的知识库问答系统。开箱即用，支持快速嵌入到第三方业务系统，1Panel 官方出品。

A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.

Unify Efficient Fine-Tuning of 100+ LLMs

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。

Leveraging large language models for text-to-SQL synthesis, this project fine-tunes WizardLM/WizardCoder-15B-V1.0 with QLoRA on a custom Spider training dataset. The resultant model, achieves 61% e…

中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。

中文langchain项目|小必应，Q.Talk，强聊，QiangTalk

Making large AI models cheaper, faster and more accessible

包含了RLHF

LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA

Implementation of Chinese ChatGPT

AgentX is an experiment to develop an autonomous agent that delegates well to Auto-GPT, babyagi, and other agents using LangChain

A full pipeline to finetune Vicuna LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the Vicuna architecture. Basically Chat…

A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the ChatGLM architecture. Basically Ch…

⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.

chatglm多gpu用deepspeed和

人工精调的中文对话数据集和一段chatglm的微调代码

在ChatGLM大模型上利用LoRA方法进行小参数学习，训练语料库选择中文的[alpaca-zh](https://huggingface.co/datasets/shibing624/alpaca-zh)

textgen, Text Generation models. 文本生成，包括：LLAMA、ChatGLM、UDA，GPT2，Seq2Seq，BART，T5等模型实现，开箱即用。