halfrot

vllm

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

Clash-for-Windows_Chinese

clash for windows汉化版. 提供clash for windows的汉化版, 汉化补丁及汉化版安装程序

scalene

Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

Qwen2

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

arxiv-latex-cleaner

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

nvitop

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

clash-for-linux-backup

基于Clash Core 制作的Clash For Linux备份仓库 A Clash For Linux Backup Warehouse Based on Clash Core

omegaconf

Flexible Python configuration system. The last one you will ever need.

DeepSeek-Coder-V2

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

OS-Copilot

An self-improving embodied conversational agent seamlessly integrated into the operating system to automate our daily tasks.

OSWorld

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

lingua-py

The most accurate natural language detection library for Python, suitable for short text and mixed-language text

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

gritlm

Generative Representational Instruction Tuning

language_tool_python

a free python grammar checker 📝✅

orpo

Official repository for ORPO

POPE

The official GitHub page for ''Evaluating Object Hallucination in Large Vision-Language Models''

research-career-tools

EnvInteractiveLMPapers

Paper collections of methods that using language to interact with environment, including interact with real world, simulated world or WWW(🏄).

Spider2-V

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

arks

exact-optimization

ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment

easy-to-hard-generalization

Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"

Directional-Preference-Alignment

Directional Preference Alignment

BRIGHT

BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

ALaRM

[ACL 2024] Code for the paper "ALaRM: Align Language Models via Hierarchical Rewards Modeling"

eval-arena

CADM-plus

CADM+: Confusion-based Learning Framework With Drift Detection and Adaptation for Real-time Safety Assessment

LLM-Distribution-Probe

An ongoing little project to probe and visualize the output distribution of LLM