Retrieval and Retrieval-augmented LLMs

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.

Reference implementation for DPO (Direct Preference Optimization)

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

Example models using DeepSpeed

[NIPS2023] RRHF & Wombat

Making large AI models cheaper, faster and more accessible

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

闻达：一个LLM调用平台。目标为针对特定环境的高效内容生成，同时考虑个人和中小企业的计算资源局限性，以及知识安全和私密性问题

Firefly: 大模型训练工具，支持训练Qwen2.5、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

Finetune Bloom big language model with Lora method

Due to restriction of LLaMA, we try to reimplement BLOOM-LoRA (much less restricted BLOOM license here https://huggingface.co/spaces/bigscience/license) using Alpaca-LoRA and Alpaca_data_cleaned.json

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

Prefix-Tuning: Optimizing Continuous Prompts for Generation

Instruct-tune LLaMA on consumer hardware

Code and documentation to train Stanford's Alpaca models, and generate the data.

基于ChatGLM-6B + LoRA的Fintune方案

Implementation of Phenaki Video, which uses Mask GIT to produce text guided videos of up to 2 minutes in length, in Pytorch

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

[ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators

Stable Diffusion web UI

Auto-GPT中文版本及爱好者组织 同步更新原项目 AI领域创业 自媒体组织 用AI工作学习创作变现

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

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

Reverse engineered ChatGPT API

Demonstrate all the questions on LeetCode in the form of animation.（用动画的形式呈现解LeetCode题目的思路）