You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Chess Reasoner LoRA

LoRA adapter for chess move prediction with structured reasoning output.

Merged model: nuriyev/chess-reasoner

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base, "nuriyev/chess-reasoner-lora")
tokenizer = AutoTokenizer.from_pretrained("nuriyev/chess-reasoner-lora")

LoRA Config

Parameter	Value
Rank	32
Alpha	64
Target Modules	q, k, v, o, gate, up, down proj

Trained with Unsloth. Next step: GRPO with Stockfish rewards.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train nuriyev/chess-reasoner-lora

Collection including nuriyev/chess-reasoner-lora

Chess Grand Master

Collection

LLM that beats humans at chess 😎 (not yet) • 6 items • Updated about 14 hours ago