genggng
A computer science PhD student of BUPT, interested in computer vision, tinyml and model quantization.
BUPTBeijing,China.
genggng's Stars
OptimalScale/LMFlow
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
modelscope/modelscope-classroom
OthersideAI/self-operating-computer
A framework to enable multimodal models to operate a computer.
LC044/WeChatMsg
提取微信聊天记录,将其导出成HTML、Word、Excel文档永久保存,对聊天记录进行分析生成年度聊天报告,用聊天数据训练专属于个人的AI聊天助手
assafelovic/gpt-researcher
GPT based autonomous agent that does online comprehensive research on any given topic
roboflow/supervision
We write your reusable computer vision tools. 💜
ollama/ollama
Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.
songquanpeng/message-pusher
搭建专属于你的消息推送服务,支持多种消息推送方式,支持 Markdown,基于 Golang 仅单可执行文件,开箱即用
tencent-connect/botpy
QQ频道机器人PythonSDK
tespent/task-notify
Capture final status and output of a possibly-long-running task, and send info to Feishu
intel-analytics/ipex-llm
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, Axolotl, etc.
intel/neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
ModelTC/QLLM
[ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models"
microsoft/JARVIS
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
overleaf/overleaf
A web-based collaborative LaTeX editor
OSVAI/KernelWarehouse
The official project website of "KernelWarehouse: Rethinking the Design of Dynamic Convolution" (KW for short, accepted to ICML 2024)
kwai/DouZero
[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI
mit-han-lab/smoothquant
[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
qwopqwop200/GPTQ-for-LLaMa
4 bits quantization of LLaMA using GPTQ
AutoGPTQ/AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
OpenGVLab/OmniQuant
[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
deborahLevy130/seathru_NeRF
official implementation of SeaThru-NeRF CVPR 2023
EleutherAI/lm-evaluation-harness
A framework for few-shot evaluation of language models.
LlamaFamily/Llama-Chinese
Llama中文社区,Llama3在线体验和微调模型已开放,实时汇总最新Llama3学习资料,已将所有代码更新适配Llama3,构建最好的中文Llama大模型,完全开源可商用
meta-llama/llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
iterative/dvc
🦉 ML Experiments and Data Management with Git
lukas-blecher/LaTeX-OCR
pix2tex: Using a ViT to convert images of equations into LaTeX code.
JamesLiao714/IPM-master
Inverse Perspective Mapping
Jittor/JittorLLMs
计图大模型推理库,具有高性能、配置要求低、中文支持好、可移植等特点
jshilong/DDQ
Dense Distinct Query for End-to-End Object Detection (CVPR2023)