Chess LoRA - chess-lora-20260112-012812 (step 6020)

Fine-tuned on chess positions to predict the best move.

Training Details

  • Base Model: Qwen/Qwen3-4B-Instruct-2507
  • Dataset: agi-noobs/chess-sft-10m-stockfish
  • Checkpoint Step: 6020

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("agi-noobs/chess-lora-20260112-012812-step6020")
tokenizer = AutoTokenizer.from_pretrained("agi-noobs/chess-lora-20260112-012812-step6020")

Trained using Tinker by Thinking Machines Lab.

Downloads last month
2
Safetensors
Model size
4B params
Tensor type
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for agi-noobs/chess-lora-20260112-012812-step6020

Adapter
(5381)
this model

Dataset used to train agi-noobs/chess-lora-20260112-012812-step6020