61 82 201

Asankhaya Sharma

codelion

http://asankhaya.github.io/

AI & ML interests

AI/ML, Dev Tools and Application Security

Recent Activity

reacted to their post with 👍 3 days ago

🧬 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. ✨ Key features: - Evolves entire codebases (not just single functions) - Works with any OpenAI-compatible API - LLM ensemble approach for better results - Multi-objective optimization 👉 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 ❤️ 3 days ago

View all activity

Organizations

codelion's activity

commented a paper 8 days ago

Phi-4 Technical Report

Paper • 2412.08905 • Published Dec 12, 2024 • 118 •

New activity in codelion/Qwen3-0.6B-pts-steering-vectors 17 days ago

Upload steering_vectors.jsonl

#1 opened 17 days ago by

codelion

New activity in codelion/Qwen3-0.6B-PTS-DPO 17 days ago

Adding `safetensors` variant of this model

#1 opened 18 days ago by

SFconvertbot

commented a paper 20 days ago

Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation

Paper • 2409.12941 • Published Sep 19, 2024 • 25 •

New activity in patched-codes/static-analysis-eval about 1 month ago

Add link to paper

#3 opened about 1 month ago by

nielsr

New activity in codelion/optillm 2 months ago

Implement other approach that optillm supported?

#5 opened 3 months ago by

melekuk

New activity in codelion/LogProbsVisualizer 3 months ago

Update app.py

#1 opened 3 months ago by

codelion

commented a paper 3 months ago

Logical Reasoning in Large Language Models: A Survey

Paper • 2502.09100 • Published Feb 13 • 23 •

New activity in deepseek-ai/Janus-Pro-1B 4 months ago

Issue with Flash attention while running Janus-Pro-1B model locally on Mac (Solved)

#8 opened 4 months ago by

saurabhksa1

commented 2 papers 4 months ago

Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?

Paper • 2502.00674 • Published Feb 2 • 13 •

Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?

Paper • 2502.00674 • Published Feb 2 • 13 •

New activity in ProsusAI/finbert 4 months ago

What do the labels mean?

#21 opened 10 months ago by

gleni2101

commented a paper 4 months ago

RouteLLM: Learning to Route LLMs with Preference Data

Paper • 2406.18665 • Published Jun 26, 2024 • 6 •

New activity in codelion/Llama-3.2-3B-o1 4 months ago

Nice! Any chance we can have access to the unquantified model files?

#1 opened 4 months ago by

Joseph717171

New activity in Qwen/QwQ-32B-Preview 4 months ago

Can't reproduce the evaluation result of GPQA dataset

➕ 1

#47 opened 5 months ago by

Rinn000

commented 4 papers 4 months ago

New activity in ShilongLiu/Grounding_DINO_demo 5 months ago

🚩 Report: Not working

#3 opened almost 2 years ago by

tommiekerssies