arxiv:2411.15221
Piyush Maharana
catastropiyush
AI & ML interests
LLMs for scientific data extraction, Solid State Hydrogen Storage,Machine Learning
Recent Activity
upvoted
an
article
about 21 hours ago
Deriving the PPO Loss from First Principles
liked
a Space
9 days ago
dlouapre/eiffel-tower-llama
liked
a model
14 days ago
openai/circuit-sparsity
Organizations
models
19
catastropiyush/dqn-SpaceInvadersNoFrameskip-v4
Reinforcement Learning
•
Updated
•
15
catastropiyush/gemma-3-finetune_GRPO
Text Generation
•
1.0B
•
Updated
•
9
catastropiyush/llama3_1_GRPO
Updated
catastropiyush/SmolLM2-FT-MyDataset
Text Generation
•
0.1B
•
Updated
•
9
catastropiyush/Reinforce_Pixelcopter
Updated
catastropiyush/Reinfroce_model
Reinforcement Learning
•
Updated
catastropiyush/llama_3_2_vision
Updated
catastropiyush/llama-3.2-3B_instruct_Q4_K_M
3B
•
Updated
•
17
catastropiyush/Marcoro14-7B-slerp
Updated
catastropiyush/Llama-3_8b_Alpaca
Text Generation
•
Updated
•
8