Stars
800,000 step-level correctness labels on LLM solutions to MATH problems
A rapid prompt app development framework based on GPT
Official codebase for "SelFee: Iterative Self-Revising LLM Empowered by Self-Feedback Generation"
Paper List for a new paradigm of NLP: Interactive NLP (https://arxiv.org/abs/2305.13246) 🔥
Unsupervised text tokenizer for Neural Network-based text generation.
Official Code for DragGAN (SIGGRAPH 2023)
Example models using DeepSpeed
Train transformer language models with reinforcement learning.
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
Notes about courses Dive into Deep Learning by Mu Li
Generate 3D objects conditioned on text or images
An annotated implementation of the Transformer paper.
A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
🦜🔗 Build context-aware reasoning applications
Instruct-tune LLaMA on consumer hardware
Code and documentation to train Stanford's Alpaca models, and generate the data.
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
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…
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Ongoing research training transformer models at scale
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
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.