tanghui315

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

Language:Python5693 56 279

🧙‍AutoDev: The AI-powered coding wizard（AI 驱动编程助手） with multilingual support 🌐, auto code generation 🏗️, and a helpful bug-slaying assistant 🐞! Customizable prompts 🎨 and a magic Auto Dev/Testing/Document/Agent feature 🧪 included! 🚀

Language:KotlinMPL-2.02763 45 156

llm-awq

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Language:PythonMIT2381 24 169

T-Rex

[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

Language:PythonNOASSERTION2166 36 84

gptq

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

Language:PythonApache-2.01889 29 48

starcoder2

Home of StarCoder2!

Language:PythonApache-2.01734 17 17

Project_CodeNet

This repository is to support contributions for tools for the Project CodeNet dataset hosted in DAX

Language:PythonApache-2.01536 55 32

GaLore

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Language:PythonApache-2.01378 18 52

LlamaGym

Fine-tune LLM agents with online reinforcement learning

Language:PythonMIT975 7 9

raptor

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Language:PythonMIT876 10 39

talk-llama-fast

Port of OpenAI's Whisper model in C/C++ with xtts and wav2lip

Language:C++MIT747 18 36

hqq

Official implementation of Half-Quadratic Quantization (HQQ)

Language:PythonApache-2.0670 16 96

MarkTool

DoTAT 是一款基于web、面向领域的通用文本标注工具，支持大规模实体标注、关系标注、事件标注、文本分类、基于字典匹配和正则匹配的自动标注以及用于实现归一化的标准名标注，同时也支持迭代标注、嵌套实体标注和嵌套事件标注。标注规范可自定义且同类型任务中可“一次创建多次复用”。通过分级实体集合扩大了实体类型的规模，并设计了全新高效的标注方式，提升了用户体验和标注效率。此外，本工具增加了审核环节，可对多人的标注结果进行一致性检验、自动合并和手动调整，提高了标注结果的准确率。

Language:VueApache-2.0590 13 18