babyagi4all
mmdeploy
| babyagi4all | mmdeploy | |
|---|---|---|
| 3 | 4 | |
| 252 | 2,571 | |
| - | 2.3% | |
| 8.3 | 7.4 | |
| about 1 year ago | about 1 month ago | |
| Python | Python | |
| MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
babyagi4all
-
Orange Pi 5 Plus Koboldcpp Demo (MPT, Falcon, Mini-Orca, Openllama)
16gb fits 30b q3_k_s. Maybe try making it work with an IQ script and have it run overnight! https://github.com/kroll-software/babyagi4all
-
An open source agent that uses Oobabooga's api for requests
Hey all, I just stumbled across this which is an open-source locally run autonomous agent like AgentGPT. It runs on CPU, but I just forked it to use Oobabooga's API instead. What this means is you can have a GPU-powered agent run locally! Check it out!
-
Open source agents! The original was just released and runs on CPU, and I forked it to work with Oobabooga's webui api, so it can be run on GPU as well!
https://github.com/kroll-software/babyagi4all is the local cpu one, which doesn't require oobabooga at all, and
mmdeploy
- [D] Object detection models that can be easily converted to CoreML
-
Orange Pi 5 Plus Koboldcpp Demo (MPT, Falcon, Mini-Orca, Openllama)
The RK3588 also has a NPU for accelerating neural networks. The bad news is the API is not supported by any of the inference engines (afaik), but the NPU can run models directly that have been converted to the RKNN format. It is a long shot, but you can find details here.
-
MMDeploy: Deploy All the Algorithms of OpenMMLab
BibTeX @misc{=mmdeploy, title={OpenMMLab's Model Deployment Toolbox.}, author={MMDeploy Contributors}, howpublished = {\url{https://github.com/open-mmlab/mmdeploy}}, year={2021} }
-
Removing the bounding box generated by OnnxRuntime segmentation
I have a semantic segmentation model trained using the mmdetection repo. Then it is converted to the ONNX format using the mmdeploy repo.
What are some alternatives?
babyagi4all-api - BabyAGI to run with locally hosted models using the API from https://github.com/oobabooga/text-generation-webui
FastDeploy - ⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization, multi-platform and multi-framework support.
text-generation-webui - A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
mmflow - OpenMMLab optical flow toolbox and benchmark
whisper.cpp - Port of OpenAI's Whisper model in C/C++
mmfewshot - OpenMMLab FewShot Learning Toolbox and Benchmark
mmdetection - OpenMMLab Detection Toolbox and Benchmark
mmpretrain - OpenMMLab Pre-training Toolbox and Benchmark
mmrotate - OpenMMLab Rotated Object Detection Toolbox and Benchmark
mmocr - OpenMMLab Text Detection, Recognition and Understanding Toolbox
ncnn - ncnn is a high-performance neural network inference framework optimized for the mobile platform
mmselfsup - OpenMMLab Self-Supervised Learning Toolbox and Benchmark