Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

✨✨Latest Advances on Multimodal Large Language Models

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

Retrieval and Retrieval-augmented LLMs

中国大模型

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…

使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。

AutoChain: Build lightweight, extensible, and testable LLM Agents

Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.

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(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

基于ChatGLM-6B的中文问诊模型

基于ChatGLM-6B + LoRA的Fintune方案

中文nlp解决方案(大模型、数据、模型、训练、推理)

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

Train transformer language models with reinforcement learning.

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

Reverse engineered ChatGPT API

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

经济学人(含音频)、纽约客、卫报、连线、大西洋月刊等英语杂志免费下载,支持epub、mobi、pdf格式, 每周更新

Tutorials on how to implement a few key architectures for image classification using PyTorch and TorchVision.

Revisiting Pre-trained Models for Chinese Natural Language Processing (MacBERT)

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/