Doctoral Researcher in Machine Learning (AIMS) at the University of Oxford with 3 years of industry experience in London-based startups.
Highlights
- Pro
Pinned Loading
-
Torch2Jax-DeepSeek-R1-Distill-Qwen-1.5B
Torch2Jax-DeepSeek-R1-Distill-Qwen-1.5B PublicFlax (Jax) implementation of DeepSeek-R1-Distill-Qwen-1.5B with weights ported from Hugging Face.
-
-
CyberAgentBreeder
CyberAgentBreeder PublicAn Evolutionary Framework for Breeding LLM Cybersecurity Agents.
Python
-
Multi-Agent-LLMs-play-20-Questions
Multi-Agent-LLMs-play-20-Questions PublicLet’s get agents to play the game of 20 questions!
Python
-
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.