Chess LoRA

Fine-tuned for chess move prediction.

Training Details

  • Prompt Template: uci_stage1_sft_prompt.jinja
  • Response Template: uci_stage1_sft_response.jinja
  • Training Steps: 12,044
  • Unique Examples: 385,408

Evaluation

Metric Value
Accuracy 0.0%
Good Moves 0.0%
ACPL (mean) 0.0
ACPL (median) 0.0

Links

  • Full details: PRIVATE_README.md
Downloads last month
1
Safetensors
Model size
4B params
Tensor type
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support