TaskMatrix
supercharger
TaskMatrix | supercharger | |
---|---|---|
10 | 13 | |
34,527 | 346 | |
0.1% | - | |
7.3 | 6.6 | |
4 months ago | about 1 year ago | |
Python | Python | |
GNU General Public License v3.0 or later | MIT License |
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.
TaskMatrix
-
How to create an automation workflow with GPT-4 image input?
I want to create a script that would automatically read telegram posts and process them, for this, using APIs these days is simply not reliable, so I'm thinking of using selenium python with the browser to do this..is there a way to develop an automated workflow that does this? I've looked in visual GPT from Microsoft https://github.com/microsoft/TaskMatrix
- TaskMatrix
- TaskMatrix Connects ChatGPT and a Series of Visual Foundation Models
-
April 2023
Low-code LLM (https://github.com/microsoft/TaskMatrix/tree/main/LowCodeLLM)
-
GPT-4 with browsing prompt
Yep, this is what Microsoft and others have done with the API to create things like bing chat. See: https://github.com/microsoft/TaskMatrix
-
[D] LLM or model that does image -> prompt?
Visual ChatGPT (now renamed as TaskMatrix https://github.com/microsoft/TaskMatrix likely as a result of OpenAI trying to regulate the use of the name GPT. Same happened for GPT-Eval -> G-Eval).
-
What’s stopping ChatGPT from replacing a bunch of jobs right now?
Microsoft is also going to connect millions of APIs. Right now software for the most part lives in silos and needs humans to move information from one software application to another. TaskMatrixAI will automate that by having a standard API schema that everyone buys into like Apple’s iOS if they want to make money. GPT and Jarvis automatically write the Python code to connect any desired APIs. https://github.com/microsoft/TaskMatrix/tree/main/TaskMatrix.AI
- 👨💻 Microsoft Researchers Propose Low-Code LLM: A Novel Human-LLM Interaction Pattern
-
Track-Anything: a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything and XMem.
microsoft/TaskMatrix (github.com)
- The repository where TaskMatrix.AI will be released just officially changed names from Visual ChatGPT to TaskMatrix. Code is probably coming soon.
supercharger
-
Claude 2
Since I've been on a AI code-helper kick recently. According to the post, Claude 2 now 71.2%, a significant upgrade from 1.3 (56.0%). It isn't specified whether this is pass@1 or pass@10.
For comparison:
* GPT-4 claims 85.4 on HumanEval, in a recent paper https://arxiv.org/pdf/2303.11366.pdf GPT-4 was tested at 80.1 pass@1 and 91 pass@1 using their Reflexion technique. They also include MBPP and Leetcode Hard benchmark comparisons
* WizardCoder, a StarCoder fine-tune is one of the top open models, scoring a 57.3 pass@1, model card here: https://huggingface.co/WizardLM/WizardCoder-15B-V1.0
* The best open model I know of atm is replit-code-instruct-glaive, a replit-code-3b fine tune, which scores a 63.5% pass@1. An independent developer abacaj has reproduced that announcement as part of code-eval, a repo for getting human-eval results: https://github.com/abacaj/code-eval
Those interested in this area may also want to take a look at this repo https://github.com/my-other-github-account/llm-humaneval-ben... that also ranks with Eval+, the CanAiCode Leaderboard https://huggingface.co/spaces/mike-ravkine/can-ai-code-resul... and airate https://github.com/catid/supercharger/tree/main/airate
Also, as with all LLM evals, to be taken with a grain of salt...
Liu, Jiawei, Chunqiu Steven Xia, Yuyao Wang, and Lingming Zhang. “Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation.” arXiv, June 12, 2023. https://doi.org/10.48550/arXiv.2305.01210.
- Let's be honest: none of the models can code well
-
April 2023
Leverage locally-hosted Large Language Models to write software + unit tests (https://github.com/catid/supercharger)
- What coding llm is the best?
-
Is there such a thing as local Llamas integrated into VSCode?
supercharger Write Software + unit tests for you, based on Baize-30B 8bit, using model parallelism
- I have a project in my own programming language, abusing both lexical and syntactic macros. I want to do a refactoring tasks on it. I don't have a GPU, but 14-core CPU. Should I pay for cloud or there are local ways to do such task on my laptop? Which model is better for programming?
- What is the best open source model/program to help index and debug code?
- Leverage locally-hosted Large Language Models to write software and unit tests
-
Can LLMs do static code analysis?
Added support for 65B LLaMa model to https://github.com/catid/supercharger tonight. It runs faster than Baize 30B (maybe due to lack of adapter) and only slightly slower than Galpaca 30B. Benchmarks here: https://docs.google.com/spreadsheets/d/1TYBNr_UPJ7wCzJThuk5ysje7K1x-_62JhBeXDbmrjA8/edit?usp=sharing
-
Benchmarks for LLMs on Consumer Hardware
Here's the code that loads it: https://github.com/catid/supercharger/blob/main/server/model_koala.py
What are some alternatives?
JARVIS - JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
developer - the first library to let you embed a developer agent in your own app!
doctorgpt - DoctorGPT brings GPT into production for application log error diagnosing!
gptest - GPTest VS Code Extension
EditAnything - Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
walter - AI-powered software development assistant built right into GitHub so it can act as your junior developer.
E2B - Secure cloud runtime for AI apps & AI agents. Fully open-source.
llm-humaneval-benchmarks
deepdoctection - A Repo For Document AI
evaporate - This repo contains data and code for the paper "Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes"
Selefra - The open-source policy-as-code software that provides analysis for Multi-Cloud and SaaS environments, you can get insight with natural language (powered by OpenAI).
locai - Connect to Kobold API through VS Code