Production ready LLM model compression/quantization toolkit with accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

视觉信息抽取任务中，使用OCR识别结果规范多模态大模型的回答

[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

Enforce the output format (JSON Schema, Regex etc) of a language model

A blazing fast inference solution for text embeddings models

Implementation of Simple Contrastive Learning-based Unsupervised approach to generate sentence embeddings and to perform text similarity in Tensorflow

Generative Representational Instruction Tuning

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

SGPT: GPT Sentence Embeddings for Semantic Search

State-of-the-Art Text Embeddings

Go ahead and axolotl questions

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

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

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

Tensors and Dynamic neural networks in Python with strong GPU acceleration

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

Fast and memory-efficient exact attention

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Toolkit for creating, sharing and using natural language prompts.

Language Models of Code are Few-Shot Commonsense Learners (EMNLP 2022)

The official gpt4free repository | various collection of powerful language models | gpt-4o and deepseek v3 & r1

Universal LLM Deployment Engine with ML Compilation

Paper List for In-context Learning 🌷

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.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

🦜🔗 Build context-aware reasoning applications

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.