Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
State-of-the-Art Text Embeddings
Tools for merging pretrained large language models.
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.
中文nlp解决方案(大模型、数据、模型、训练、推理)
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
QLoRA: Efficient Finetuning of Quantized LLMs
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)