Lists (13)
Stars
🦜🔗 The platform for reliable agents.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
A high-throughput and memory-efficient inference and serving engine for LLMs
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
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…
We write your reusable computer vision tools. 💜
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
OpenMMLab Detection Toolbox and Benchmark
Code and documentation to train Stanford's Alpaca models, and generate the data.
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
Code for the paper "Language Models are Unsupervised Multitask Learners"
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
An open source implementation of CLIP.
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.
Hackable and optimized Transformers building blocks, supporting a composable construction.