Official implementation of paper "On the Diagram of Thought" (https://arxiv.org/abs/2409.10038)

欢迎来到 LLM-Dojo，这里是一个开源大模型学习场所，使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩‍🎓👨‍🎓

Use PEFT or Full-parameter to finetune 350+ LLMs or 90+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-Vi…

[ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.

awesome-autonomous-driving

🔥 AgentScale: A Scalable Microservices-based Agent Orchestration Framework

一个适合学习、使用、自主扩展的RAG【检索增强生成】系统！可联网做AI搜索

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

LLM&VLM Tutorial

This is the official repo for "PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization". PromptAgent is a novel automatic prompt optimization method that auton…

A library for advanced large language model reasoning

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

The offical realization of InstructERC

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

This repo contains implementation of different architectures for emotion recognition in conversations.

Llama3-Tutorial（XTuner、LMDeploy、OpenCompass）

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

医学影像数据集列表 『An Index for Medical Imaging Datasets』

中文长文本摘要数据集 / 社科论文-摘要数据集

《明日方舟》小助手，全日常一键长草！| A one-click tool for the daily tasks of Arknights, supporting all clients.

Implementation of Parti, Google's pure attention-based text-to-image neural network, in Pytorch

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Taming Transformers for High-Resolution Image Synthesis

本项目旨在分享大模型相关技术原理以及实战经验。

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

An unofficial implementation of both ViT-VQGAN and RQ-VAE in Pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch