kyegomez/algorithm-of-thoughts

My implementation of "Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models"

Welcome to My Github 🙏

Purpose

• Advancing Humanity through Research: My purpose is to accelerate Humanity through artificial intelligence, nanotechnology, and bioengineering.

Occupation

• Professional and Community Engagement: Learn about my professional roles and how you can engage with the community.
  • Swarms - Workflow Automation
  • Agora, the multi-modal AI research lab

Support my Work

• Support My Initiatives: Various ways to support my projects and continued open-source contributions.
  • Sponsor my GitHub Projects
  • Financial Support for Backlog Elimination
  • Follow me on Twitter for AI Insights
  • Watch New Demos on YouTube
  • Schedule a Consultation for Custom AI Solutions
  • 

Unfinished Paper Implementations:

• Soundstream
• Gato
• Autort
• self extend
• GATS
• USM Implementation of Google's USM speech model in Pytorch
• VIMA
• SayCan
• gen2 + gen1
• vision mamba
• MoE Mamba
• SwitchTransformer
• Midas
• tritontransformer
• HRTX
• Morpheus
• Drone UAV swarm model in swarms-pytorch: https://github.com/Zhehui-Huang/quad-swarm-rl
• M2PT
• UNetMamba
• Lumiere
• MCVIT
• Hedgehog
• Vit-RGTS
• MambaByte
• VideoVIT
• Hedgehog
• LiMoE
• Sora
• DSH
• EchoPulse
• Algorithm of Thoughts
• Simple Mamba
• Vision Llama
• BitNet
• Griffin
• MM1
• Gamba
• ViTar
• CT
• MHMoE
• xLSTM
• AlphaFold3
• InfiniAttention
• Pairformer

Glory to God ✝️

algorithm-of-thoughts's Issues

Is that possible make it work with codellama34b?

Is that possible make it work with codellama34b?

Also, hows the result as for Chinese llm model?

Upvote & Fund

• We're using Polar.sh so you can upvote and help fund this issue.
• We receive the funding once the issue is completed & confirmed by you.
• Thank you in advance for helping prioritize & fund our backlog.

DFS

Would you explain what you mean by: "DFS search similar to Algorithm of thoughts"?

Thanks in advance

Upvote & Fund

• We're using Polar.sh so you can upvote and help fund this issue.
• We receive the funding once the issue is completed & confirmed by you.
• Thank you in advance for helping prioritize & fund our backlog.

Confirm you do not plan to stop spamming people.

Hi @kyegomez, you closed kyegomez/swarms#62 about you spamming people as "not planned". Can you confirm that you do not intent to take any action?

Please take a look at:

• https://www.fcc.gov/general/can-spam
• https://ico.org.uk/for-the-public/online/spam-emails/

It would be great if you stopped.

Please stop spamming me, and others. Also see kyegomez/swarms#40

Upvote & Fund

• We're using Polar.sh so you can upvote and help fund this issue.
• We receive the funding once the issue is completed & confirmed by you.
• Thank you in advance for helping prioritize & fund our backlog.

Compare with GPT-4 Advanced Data Analysis (integrating with Python)

This wasn't tested in the original paper, but I've found GPT+4 with Python (Advanced Data Analysis) is often capable of solving these kinds of problems by writing a Python program that finds the solution in the search space:

• https://chat.openai.com/c/010d05d3-63f4-4825-9d4c-4f3bead36e7b

Here, GPT wrote a Python program that tries all permutations of the expression (A^B)^(C^D), where "^" are one of the four basic arithmetic operators (+,-,*,/) and A, B, C, D are a permutation of the given numbers.

It then found the solution (14 - 8) * (8 / 2) = 24, which is correct. And this is in a relatively small number of tokens (input = 112 tokens, output = 512 + prompt for Advanced Data Analysis >= 624 tokens), whereas AoT would likely require far more (the openai.logs file in this repo, for instance, is 15 306 tokens).

Upvote & Fund

• We're using Polar.sh so you can upvote and help fund this issue.
• We receive the funding once the issue is completed & confirmed by you.
• Thank you in advance for helping prioritize & fund our backlog.