SolidGPT
Finetune_LLMs
SolidGPT | Finetune_LLMs | |
---|---|---|
9 | 2 | |
1,951 | 442 | |
3.9% | - | |
8.6 | 8.5 | |
about 2 months ago | about 2 months ago | |
Python | Python | |
Creative Commons Attribution 4.0 | GNU Affero General Public License v3.0 |
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.
SolidGPT
-
Best coding AI to use with entire codebase
Another thing to try is one of the repositories like SolidGPT: https://github.com/AI-Citizen/SolidGPT
- SolidGPT-Chat everything with your code repository, get repository level answer
-
MetaGPT VS SolidGPT - a user suggested alternative
2 projects | 23 Oct 2023
Compared to the MetaGPT, SolidGPT allow user to realize a function or a requirement from the code base and providing a detail code plan based on the previous code base. The generate code style is quite similar to the other product
-
SolidGPT - An new published open source human-AI collaboration multi-agent framework. Working with Notion, Lowdefy, SolidGPT can brainstorm, write PRD HLD, create Kanban, create tasks to Accelerate your software development SOP.
Github: https://github.com/AI-Citizen/SolidGPT
-
LLM Agent and Notion = Standard Software Development Booster
SolidGPT - An new published open source human-AI collaboration multi-agent framework. Working with Notion, Lowdefy, SolidGPT can brainstorm, write PRD HLD, create Kanban, create tasks to Accelerate your software development SOP.
AI Agent + Notion = Standard Software Development Booster
Check it out on our Github repo explore how Notion work with LLM agent to finish the greate work! : https://github.com/AI-Citizen/SolidGPT
Please star us if you like it and no hesitate give us your feedback, appreciate enjoy!
- SolidGPT – AI-human collaboration framework. Boost your software SOP
-
An open source human-AI collaboration framework. Build and work with your 🧱 LLMs agent team.
Github: [https://github.com/AI-Citizen/SolidGPT](https://github.com/AI-Citizen/SolidGPT)SolidGPT is a multi-agent framework that allows users to customize the LLM agent and workflow, facilitating deep interactions during task processing. Currently, it's optimized for software development, covering tasks from ideation to implementation.
Finetune_LLMs
-
Prepare Dataset
Regarding this: if you have resources (at least Colab Pro), you would be much better off training GPT-J (aka GPT-J-6B). Not only it's 4x larger than the largest GPT-2, its architecture, AFAIK, is based on GPT-3. You can use this repo as a good example for GPT-J finetuning.
-
[D] Fine-tuning GPT-J: lessons learned
And this: https://github.com/mallorbc/Finetune_GPTNEO_GPTJ6B
What are some alternatives?
MetaGPT - 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
go-llama2 - Llama 2 inference in one file of pure Go
mesh-transformer-jax - Model parallel transformers in JAX and Haiku
CUPCAKEAGI - 🧁👋 Welcome to CupcakeAGI, where we bake up some sweet and creamy AGI goodness! 🍰🤖
code-llama-for-vscode - Use Code Llama with Visual Studio Code and the Continue extension. A local LLM alternative to GitHub Copilot.
Roy - Roy: A lightweight, model-agnostic framework for crafting advanced multi-agent systems using large language models.
AnglE - Angle-optimized Text Embeddings | 🔥 SOTA on STS and MTEB Leaderboard
Chrome-GPT - An AutoGPT agent that controls Chrome on your desktop
GoLLIE - Guideline following Large Language Model for Information Extraction
BlockAGI - Your Self-Hosted, Hackable Research Agent Inspired by AutoGPT
replicate-llama2-sms-chatbot