Hugging Face's logo
Asankhaya Sharma's picture
61 82 201

Asankhaya Sharma

codelion
Meka-1018's profile picture Webvoom12's profile picture mhaisaac45's profile picture
Ā·
http://asankhaya.github.io/

AI & ML interests

AI/ML, Dev Tools and Application Security

Recent Activity

reacted to their post with šŸ‘ 3 days ago
šŸ§¬ Hey everyone! Just released **OpenEvolve** - an open-source implementation of Google DeepMind's AlphaEvolve system. It's an evolutionary coding agent that uses LLMs to discover and optimize algorithms. I successfully replicated DeepMind's results on circle packing (99.97% match!) and evolved a random search into a simulated annealing algorithm. āœØ Key features: - Evolves entire codebases (not just single functions) - Works with any OpenAI-compatible API - LLM ensemble approach for better results - Multi-objective optimization šŸ‘‰ Check it out: GitHub: https://github.com/codelion/openevolve Blog post: https://huggingface.co/blog/codelion/openevolve Would love to hear your thoughts or answer any questions about it!
upvoted a paper 3 days ago
Chain-of-Model Learning for Language Model
reacted to their post with ā¤ļø 3 days ago
šŸ§¬ Hey everyone! Just released **OpenEvolve** - an open-source implementation of Google DeepMind's AlphaEvolve system. It's an evolutionary coding agent that uses LLMs to discover and optimize algorithms. I successfully replicated DeepMind's results on circle packing (99.97% match!) and evolved a random search into a simulated annealing algorithm. āœØ Key features: - Evolves entire codebases (not just single functions) - Works with any OpenAI-compatible API - LLM ensemble approach for better results - Multi-objective optimization šŸ‘‰ Check it out: GitHub: https://github.com/codelion/openevolve Blog post: https://huggingface.co/blog/codelion/openevolve Would love to hear your thoughts or answer any questions about it!
View all activity

Organizations

meraGPT's profile picture Lambda Security's profile picture National University of Singapore's profile picture Patched's profile picture ZeroGPU Explorers's profile picture MLX Community's profile picture Social Post Explorers's profile picture Hugging Face Discord Community's profile picture Adaptive Classifier's profile picture Reasoning datasets competition 's profile picture Cerebras Hugging Face Hackathon's profile picture

codelion's activity

reacted to their post with šŸ‘ 3 days ago
view post
Post
2681
šŸ§¬ Hey everyone! Just released **OpenEvolve** - an open-source implementation of Google DeepMind's AlphaEvolve system.

It's an evolutionary coding agent that uses LLMs to discover and optimize algorithms. I successfully replicated DeepMind's results on circle packing (99.97% match!) and evolved a random search into a simulated annealing algorithm.

āœØ Key features:
- Evolves entire codebases (not just single functions)
- Works with any OpenAI-compatible API
- LLM ensemble approach for better results
- Multi-objective optimization

šŸ‘‰ Check it out:
GitHub: https://github.com/codelion/openevolve
Blog post: https://huggingface.co/blog/codelion/openevolve

Would love to hear your thoughts or answer any questions about it!
upvoted a paper 3 days ago
reacted to their post with ā¤ļøšŸ‘€šŸš€šŸ”„ 3 days ago
view post
Post
2681
šŸ§¬ Hey everyone! Just released **OpenEvolve** - an open-source implementation of Google DeepMind's AlphaEvolve system.

It's an evolutionary coding agent that uses LLMs to discover and optimize algorithms. I successfully replicated DeepMind's results on circle packing (99.97% match!) and evolved a random search into a simulated annealing algorithm.

āœØ Key features:
- Evolves entire codebases (not just single functions)
- Works with any OpenAI-compatible API
- LLM ensemble approach for better results
- Multi-objective optimization

šŸ‘‰ Check it out:
GitHub: https://github.com/codelion/openevolve
Blog post: https://huggingface.co/blog/codelion/openevolve

Would love to hear your thoughts or answer any questions about it!
posted an update 3 days ago
view post
Post
2681
šŸ§¬ Hey everyone! Just released **OpenEvolve** - an open-source implementation of Google DeepMind's AlphaEvolve system.

It's an evolutionary coding agent that uses LLMs to discover and optimize algorithms. I successfully replicated DeepMind's results on circle packing (99.97% match!) and evolved a random search into a simulated annealing algorithm.

āœØ Key features:
- Evolves entire codebases (not just single functions)
- Works with any OpenAI-compatible API
- LLM ensemble approach for better results
- Multi-objective optimization

šŸ‘‰ Check it out:
GitHub: https://github.com/codelion/openevolve
Blog post: https://huggingface.co/blog/codelion/openevolve

Would love to hear your thoughts or answer any questions about it!
upvoted an article 4 days ago
view article
Article

OpenEvolve: An Open Source Implementation of Google DeepMind's AlphaEvolve

By codelion ā€¢
ā€¢ 11
published an article 4 days ago
view article
Article

OpenEvolve: An Open Source Implementation of Google DeepMind's AlphaEvolve

By codelion ā€¢
ā€¢ 11
updated 3 datasets 4 days ago
reacted to their post with ā¤ļøšŸ‘€šŸš€šŸ”„ 5 days ago
view post
Post
2326
Introducing Pivotal Token Search (PTS): A new technique for targeted LLM alignment

Excited to share Pivotal Token Search (PTS), a technique for identifying and optimizing critical decision points in LLM generations!

GitHub repository: https://github.com/codelion/pts

What is PTS?
PTS helps identify specific "pivotal tokens" that dramatically shift the probability of a successful generation. Unlike traditional DPO which treats all tokens equally, PTS focuses optimization on the tokens that actually matter for success.

Inspired by Microsoft's recent Phi-4 paper (which used this technique to achieve SOTA reasoning with only 14B parameters), PTS is especially effective for:
- Mathematical reasoning
- Coding tasks
- Multi-step problem solving
- Any domain where specific decision points strongly impact outcomes

What we're releasing today: codelion/pivotal-token-search-68241145d8b8502122f3ce4f

1. Open-source code:
- Complete implementation of the PTS algorithm
- Data generation pipelines
- Usage examples and documentation

2. Huggingface resources:
- Datasets collection: https://huggingface.co/datasets?other=pts
* Pre-generated preference pairs for various domains
* Ready to use in your DPO training pipelines

- Models collection: https://huggingface.co/models?other=pts
* Pre-trained models fine-tuned with PTS
* Specialized versions for different reasoning tasks

The algorithm is straightforward to implement and can significantly improve your model's reasoning capabilities. Check out the repository for details on getting started!

We welcome feedback, contributions, and collaborations. Let us know if you use PTS in your projects!
posted an update 5 days ago
view post
Post
2326
Introducing Pivotal Token Search (PTS): A new technique for targeted LLM alignment

Excited to share Pivotal Token Search (PTS), a technique for identifying and optimizing critical decision points in LLM generations!

GitHub repository: https://github.com/codelion/pts

What is PTS?
PTS helps identify specific "pivotal tokens" that dramatically shift the probability of a successful generation. Unlike traditional DPO which treats all tokens equally, PTS focuses optimization on the tokens that actually matter for success.

Inspired by Microsoft's recent Phi-4 paper (which used this technique to achieve SOTA reasoning with only 14B parameters), PTS is especially effective for:
- Mathematical reasoning
- Coding tasks
- Multi-step problem solving
- Any domain where specific decision points strongly impact outcomes

What we're releasing today: codelion/pivotal-token-search-68241145d8b8502122f3ce4f

1. Open-source code:
- Complete implementation of the PTS algorithm
- Data generation pipelines
- Usage examples and documentation

2. Huggingface resources:
- Datasets collection: https://huggingface.co/datasets?other=pts
* Pre-generated preference pairs for various domains
* Ready to use in your DPO training pipelines

- Models collection: https://huggingface.co/models?other=pts
* Pre-trained models fine-tuned with PTS
* Specialized versions for different reasoning tasks

The algorithm is straightforward to implement and can significantly improve your model's reasoning capabilities. Check out the repository for details on getting started!

We welcome feedback, contributions, and collaborations. Let us know if you use PTS in your projects!
updated a Space 6 days ago