This is a LoRA-trained model based on Qwen2.5-14B-Instruct, fine-tuned to analyze chess positions and suggest moves. The model was trained using GRPO (Guided Reward Proximal Optimization) to maximize move quality as evaluated by Stockfish.
Model Details
Base Model: Qwen/Qwen2.5-14B-Instruct
Training Method: LoRA with GRPO
Training Data: Generated chess positions with Stockfish evaluations
Input Format: Chess positions in FEN notation with ASCII board visualization
Output Format:
<think>
Analysis of the position
</think>
<move>
Chosen move in UCI format (e.g., e2e4)
</move>
Usage
python
1from unsloth import FastLanguageModel
2from safetensors.torch import load_file
34# Load the base model5model, tokenizer = FastLanguageModel.from_pretrained(6 model_name="Qwen/Qwen2.5-14B-Instruct",7 max_seq_length=1024,8 load_in_4bit=True,9 fast_inference=True10)1112# Get PEFT model with LoRA configuration13model = FastLanguageModel.get_peft_model(14 model,15 r=64,16 target_modules=["q_proj","k_proj","v_proj","o_proj","gate_proj","up_proj","down_proj"],17 lora_alpha=6418)1920# Load the LoRA weights21state_dict = load_file("adapter_model.safetensors")22model.load_state_dict(state_dict)
Training
The model was trained on chess positions with rewards based on move quality as evaluated by Stockfish. The reward function considers:
Move legality
Move syntax
Move quality (compared to Stockfish's top 3 moves)
License
This model inherits the license of the base Qwen2.5-14B-Instruct model.
Model Card for Model ID
Model Details
Model Description
Developed by: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Finetuned from model [optional]: [More Information Needed]
Model Sources [optional]
Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]
Uses
Direct Use
[More Information Needed]
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
