Void Soul's starred repositories
OpenMMLabCourse
OpenMMLab course index and stuff
mmsegmentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
face-parsing.PyTorch
Using modified BiSeNet for face parsing in PyTorch
dive-into-llms
《动手学大模型Dive into LLMs》系列编程实践教程
python-onvif-zeep
ONVIF Client Implementation in Python 2+3 (using https://github.com/mvantellingen/python-zeep instead of suds as SOAP client)
inference
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop.
FlagEmbedding
Retrieval and Retrieval-augmented LLMs
agentscope
Start building LLM-empowered multi-agent applications in an easier way.
Multi-Agent-GPT
Multi-Agent-GPT: 一款基于RAG和agent构建的多模态专家助手GPT。它集成了文本、图像和音频等模态工具。支持本地部署和私有数据库建设。
LLaMA-Factory
Unify Efficient Fine-Tuning of 100+ LLMs
clash-verge-rev
Continuation of Clash Verge - A Clash Meta GUI based on Tauri (Windows, MacOS, Linux)
llm-resource
LLM全栈优质资源汇总
llama3-chinese
Llama3-Chinese是以Meta-Llama-3-8B为底座,使用 DORA + LORA+ 的训练方法,在50w高质量中文多轮SFT数据 + 10w英文多轮SFT数据 + 2000单轮自我认知数据训练而来的大模型。
chinese-llm-benchmark
中文大模型能力评测榜单:覆盖百度文心一言、chatgpt、阿里通义千问、讯飞星火、belle / chatglm6b 等开源大模型,多维度能力评测。不仅提供能力评分排行榜,也提供所有模型的原始输出结果!
LocalChatDev
A version of the ChatDev framework modified to work locally or in private networks of user-hosted ai model instances.
Labelme2YOLO
Help converting LabelMe Annotation Tool JSON format to YOLO text file format. If you've already marked your segmentation dataset by LabelMe, it's easy to use this tool to help converting to YOLO format dataset.