loopgpt
supercharger
loopgpt | supercharger | |
---|---|---|
20 | 13 | |
1,391 | 346 | |
- | - | |
8.5 | 6.6 | |
about 2 months ago | about 1 year ago | |
Python | Python | |
MIT License | 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.
loopgpt
-
[P] LoopGPT Update - Finally something useful?
So we thought it would be a good idea to create a framework that makes use of LoopGPT agent's memory and custom tooling capabilities. Let's jump right into the new features of this framework.
-
April 2023
LoopGPT Modular Auto-GPT Framework (https://github.com/farizrahman4u/loopgpt)
-
Has anyone set Auto GPT with the Azure OpenAI service?
We just added Azure OpenAI support on our modular reimplementation of Auto-GPT: LoopGPT. And I think it's much easier to setup using our python API because you can just use the copy-paste that you can get from "View code" on the Chat Playground on Azure. Here's the whole snippet that you need to use.
-
How do I get autogpt to start exactly where it left off?
I suggest using LoopGPT, a GPT-3.5 friendly, modular re-implementation of Auto-GPT (this is self-promotion, I am a co-author FYI :). We have full state serialization which means you can save your agent state completely and start right from where you left off. To get started just do
-
Machine Learning Engineer Answers Your Questions Episode 2
As another MLE, who's working on an Auto-GPT inspired project, I want to say that I totally understand this technology (atleast with GPT-3.5) is not great. This is why we focused on building a better codebase, which is extensibile, modular and is just an overall more "Pythonic" reimplementation of Auto-GPT rather than trying to claim to be perfect. Although, I must mention that people have had better results with LoopGPT with both GPT-3.5 and GPT-4, and we don't even have GPT-4!
-
is GPT 4 api necessary ?
I suggest you try LoopGPT - It works better on GPT-3.5 according to many users. We have a nice little discord too where you can post any issues: https://discord.gg/rqs26cqx7v
-
Can not install Auto GPT(as well as Baby AGI)...
Glad you got it figured out. Please also try out LoopGPT if you can - it works better with GPT-3.5
-
crap-gpt?
This 100%. Also, AutoGPT is not the best option when you want to add more capability, LoopGPT is as it has a framework to easily add more capabilities (called tools).
- cant get autogpt to run :/
-
LLaMA support on LoopGPT
We recently released a GPT-3.5-friendly reimplementation of Auto-GPT, a "Pythonic" modular framework called LoopGPT that supports adding custom tools. Our first-time users tell us it produces better results compared to Auto-GPT on both GPT-3.5 as well as GPT-4.
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. βIs Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation.β 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?
AutoGPT - AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
developer - the first library to let you embed a developer agent in your own app!
babyagi
gptest - GPTest VS Code Extension
Auto-GPT - An experimental open-source attempt to make GPT-4 fully autonomous. [Moved to: https://github.com/Significant-Gravitas/AutoGPT]
walter - AI-powered software development assistant built right into GitHub so it can act as your junior developer.
AgentGPT - π€ Assemble, configure, and deploy autonomous AI Agents in your browser.
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"
Auto-GPT - An experimental open-source attempt to make GPT-4 fully autonomous. [Moved to: https://github.com/Significant-Gravitas/Auto-GPT]
locai - Connect to Kobold API through VS Code