An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

Robust recipes to align language models with human and AI preferences

A high-throughput and memory-efficient inference and serving engine for LLMs

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

PC微信Hook模块、Hook WeChat / 微信逆向、微信机器人、WeChatRobot

attention_sinks can use autogptq,and support all model at autogptq,like qwen baichuan,etc

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

vits2 backbone with bert