Tools for merging pretrained large language models.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Fast and memory-efficient exact attention

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, llama.cpp (GGUF), Llama models.

An experimental open-source attempt to make GPT-4 fully autonomous.

Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)

🩹Editing large language models within 10 seconds⚡

纯c++的全平台llm加速库，chatglm-6B级模型单卡可达10000+token / s，支持moss, chatglm, baichuan模型，手机端流畅运行

百亿参数的中英文双语基座大模型

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.

Live Training for Open-source Big Models

Model Compression for Big Models

Easily share permanent links to ChatGPT conversations with your friends

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

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

Panda: 海外中文开源大语言模型，基于 Llama-7B, -13B, -33B, -65B 进行中文领域上的持续预训练。

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

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

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

Making big AI models cheaper, easier, and scalable

Reduce the size of pretrained Hugging Face models via vocabulary trimming.

An unofficial Python wrapper for OpenAI's ChatGPT API

A framework for few-shot evaluation of autoregressive language models.

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

Existing Literature about Machine Unlearning

A Neural Framework for MT Evaluation

A web-based collaborative LaTeX editor