chess_mid_rl

~95% first gen accuracy via excessive RL training 🥱 Chess model submitted to the LLM Course Chess Challenge.

Submission Info

• Submitted by: j0eyd
• Parameters: 969,600
• Organization: LLM-course

Model Details

• Architecture: Chess Transformer (GPT-style)
• Vocab size: 72
• Embedding dim: 128
• Layers: 7
• Heads: 8