Martins6/ppo-LunarLander-v2
Reinforcement Learning • Updated • 8
Adriel Martins
Martins6
AI & ML interests
Graph Neural Networks (GNN) &
Robot Learning &
Multimodal AI
Recent Activity
reacted to DedeProGames's post with 🤗 2 days ago
Can small models program?
Although even if they are reasoning AIs, small AIs cannot create extensive and high-quality code, at least that's what is commonly thought.
We present https://huggingface.co/OrionLLM/NanoCoder-0.6b, an AI with just 600 million parameters based on qwen3-0.6b and trained with the dataset https://huggingface.co/datasets/nvidia/OpenCodeReasoning.
While not good at complex code, we observed a significant improvement in code generation (especially in Python code), demonstrating that, when trained correctly, small AIs can, in fact, program. liked a model 2 days ago
cerebras/GLM-4.6-REAP-218B-A32B liked a model 2 days ago
0xSero/MiniMax-M2.1-REAP-40Organizations
None yet