chess-behemoth-666

Chess model submitted to the LLM Course Chess Challenge.

Submission Info

• Submitted by: rifaki
• Parameters: 948,353
• Organization: LLM-course

Model Details

• Architecture: Chess Transformer (GPT-style)
• Vocab size: 85
• Embedding dim: 128
• Layers: 6
• Heads: 4
• FFN inner dim: 320
• Context length: 256
• Dropout: 0.09

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("LLM-course/chess-behemoth-666", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("LLM-course/chess-behemoth-666", trust_remote_code=True)