SuperAGI
transformers
SuperAGI | transformers | |
---|---|---|
82 | 176 | |
14,491 | 125,369 | |
- | 1.7% | |
9.8 | 10.0 | |
6 days ago | 3 days 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.
SuperAGI
- Introducing GPTs
-
🐍🐍 23 issues to grow yourself as an exceptional open-source Python expert 🧑💻 🥇
Repo : https://github.com/TransformerOptimus/SuperAGI
-
Introduction to Agent Summary – Improving Agent Output by Using LTS & STM
The recent introduction of the “Agent Summary” feature in SuperAGI version 0.0.10 has brought a drastic difference in agent performance – improving the quality of agent output. Agent Summary helps AI agents maintain a larger context about their goals while executing complex tasks that require longer conversations (iterations).
-
🚀✨SuperAGI v0.0.10✨is now live on GitHub
Checkout the full release here: https://github.com/TransformerOptimus/SuperAGI/releases/tag/v0.0.10
-
Top 20 Must Try AI Tools for Developers in 2023
10. SuperAGI
-
We're bringing in Google 's PaLM2 🦬 Bison LLM API support into SuperAGI in our upcoming v0.0.8 release
Currently, PaLM2 Bison is live on the dev branch of SuperAGI GitHub for the community to try: https://github.com/TransformerOptimus/SuperAGI/tree/dev
-
Why use SuperAGI
SuperAGI is made with developers in mind, therefore it takes into account their requirements and preferences when making autonomous AI agents. It has a number of advantages, including:
- In five years, there will be no programmers left, believes Stability AI CEO
-
LLM Powered Autonomous Agents
I think for agents to truly find adoption in real world, agent trajectory fine tuning is critical component - how do you make an agent perform better to achieve particular objective with every subsequent run. Basically making the agents learn similar to how we learn when we
Also I think current LLMs might not fit well for agent use cases in mid to long term because the RL they go through is based on input-best output methods whereas the intelligence that you need in agents is more around how to build an algorithm to achieve an objective on the fly - this requires perhaps new type of large models ( Large Agent Models ? ) which are trained using RLfD ( Reinforcement Learning from demonstration )
Also I think one of the key missing piece is a highly configurable software middle ware between Intelligence ( LLMs ), Memory ( Vector Dbs ~LTMs, STMs ), Tools and workflows across every iteration. Current agent core loop to find next best action is too simplistic. For example if core self prompting loop or iteration of an agent can be configured for the use case in hand. Eg for BabyAGI, every iteration goes through workflow of Plan, Prioritize and Execute or in AutoGPT it finds the next best action based on LTM/STM, or GPTEngineer it is to write specs > write tests > write code. Now for dev infra monitoring agent this workflow might be totally different - it would look like consume logs from different tools like Grafana, Splunk, APMs > See if it doesnt have an anomaly > if it has an anomaly then take human input for feedback. Every use case in real world has it's own workflow and current construct of agent frameworks have this thing hard coded in base prompt. In SuperAGI( https://superagi.com) ( disclaimer : Im creator of it ), core iteration workflow of agent can be defined as part of agent provisioning.
Another missing piece is notion of Knowledge. Agents currently depend entirely upon knowledge of LLMs or search results to execute on tasks, but if a specialised knowledge set is plugged to an agent, it performs significantly better.
-
Created a simple chrome dino game using SuperAGI's SuperCoder 😵 The dino changes color on every run :P (without writing a single line of code myself)
Build your own game here: https://github.com/TransformerOptimus/SuperAGI
transformers
-
AI enthusiasm #9 - A multilingual chatbot📣🈸
transformers is a package by Hugging Face, that helps you interact with models on HF Hub (GitHub)
-
Maxtext: A simple, performant and scalable Jax LLM
Is t5x an encoder/decoder architecture?
Some more general options.
The Flax ecosystem
https://github.com/google/flax?tab=readme-ov-file
or dm-haiku
https://github.com/google-deepmind/dm-haiku
were some of the best developed communities in the Jax AI field
Perhaps the “trax” repo? https://github.com/google/trax
Some HF examples https://github.com/huggingface/transformers/tree/main/exampl...
Sadly it seems much of the work is proprietary these days, but one example could be Grok-1, if you customize the details. https://github.com/xai-org/grok-1/blob/main/run.py
-
Lossless Acceleration of LLM via Adaptive N-Gram Parallel Decoding
The HuggingFace transformers library already has support for a similar method called prompt lookup decoding that uses the existing context to generate an ngram model: https://github.com/huggingface/transformers/issues/27722
I don't think it would be that hard to switch it out for a pretrained ngram model.
-
AI enthusiasm #6 - Finetune any LLM you want💡
Most of this tutorial is based on Hugging Face course about Transformers and on Niels Rogge's Transformers tutorials: make sure to check their work and give them a star on GitHub, if you please ❤️
-
Schedule-Free Learning – A New Way to Train
* Superconvergence + LR range finder + Fast AI's Ranger21 optimizer was the goto optimizer for CNNs, and worked fabulously well, but on transformers, the learning rate range finder sadi 1e-3 was the best, whilst 1e-5 was better. However, the 1 cycle learning rate stuck. https://github.com/huggingface/transformers/issues/16013
-
Gemma doesn't suck anymore – 8 bug fixes
Thanks! :) I'm pushing them into transformers, pytorch-gemma and collabing with the Gemma team to resolve all the issues :)
The RoPE fix should already be in transformers 4.38.2: https://github.com/huggingface/transformers/pull/29285
My main PR for transformers which fixes most of the issues (some still left): https://github.com/huggingface/transformers/pull/29402
- HuggingFace Transformers: Qwen2
- HuggingFace Transformers Release v4.36: Mixtral, Llava/BakLlava, SeamlessM4T v2
- HuggingFace: Support for the Mixtral Moe
-
Paris-Based Startup and OpenAI Competitor Mistral AI Valued at $2B
If you want to tinker with the architecture Hugging Face has a FOSS implementation in transformers: https://github.com/huggingface/transformers/blob/main/src/tr...
If you want to reproduce the training pipeline, you couldn't do that even if you wanted to because you don't have access to thousands of A100s.
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.
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Auto-GPT - An experimental open-source attempt to make GPT-4 fully autonomous. [Moved to: https://github.com/Significant-Gravitas/AutoGPT]
sentence-transformers - Multilingual Sentence & Image Embeddings with BERT
autogen - A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap
llama - Inference code for Llama models
Auto-GPT - An experimental open-source attempt to make GPT-4 fully autonomous. [Moved to: https://github.com/Significant-Gravitas/Auto-GPT]
transformer-pytorch - Transformer: PyTorch Implementation of "Attention Is All You Need"
AgentGPT - 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
AutoLearn-GPT - ChatGPT learns automatically.
huggingface_hub - The official Python client for the Huggingface Hub.