Chess LoRA - chess-grpo-20260113-023026 (step 49)
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: 49
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("agi-noobs/chess-grpo-20260113-023026-step49")
tokenizer = AutoTokenizer.from_pretrained("agi-noobs/chess-grpo-20260113-023026-step49")
Trained using Tinker by Thinking Machines Lab.
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for agi-noobs/chess-grpo-20260113-023026-step49
Base model
Qwen/Qwen3-4B-Instruct-2507