Instructions to use SBellilty/llm-chess-agent-v3-half-training with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SBellilty/llm-chess-agent-v3-half-training with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SBellilty/llm-chess-agent-v3-half-training")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SBellilty/llm-chess-agent-v3-half-training")
model = AutoModelForCausalLM.from_pretrained("SBellilty/llm-chess-agent-v3-half-training")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SBellilty/llm-chess-agent-v3-half-training with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SBellilty/llm-chess-agent-v3-half-training"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SBellilty/llm-chess-agent-v3-half-training",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SBellilty/llm-chess-agent-v3-half-training

SGLang

How to use SBellilty/llm-chess-agent-v3-half-training with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SBellilty/llm-chess-agent-v3-half-training" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SBellilty/llm-chess-agent-v3-half-training",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SBellilty/llm-chess-agent-v3-half-training" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SBellilty/llm-chess-agent-v3-half-training",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SBellilty/llm-chess-agent-v3-half-training with Docker Model Runner:
```
docker model run hf.co/SBellilty/llm-chess-agent-v3-half-training
```

LLM Chess Agent - Global Chess Challenge 2025

This model is a fine-tuned chess agent for the Global Chess Challenge 2025.

🎯 Architecture

Base Model: Qwen/Qwen2.5-1.5B-Instruct
Method: LoRA fine-tuning (rank 8, alpha 16)
Approach: Constrained ranking via log-probability scoring
Guarantees:
- ✅ 100% legal moves (by construction)
- ✅ 100% correct format

🎮 How It Works

The agent uses constrained ranking instead of free generation:

Environment provides: FEN + side + list of legal moves
Agent scores each candidate move via log-probability
Agent selects: best_move = argmax(scores)
Result: Always legal (move is always in the provided list)

📊 Performance

Legality: 100% (guaranteed by constrained ranking)
Format: 100% (hardcoded output)
Top-1 Accuracy: ~70-80% (vs Stockfish depth 10)
ACPL: ~100-150 centipawns
Playing Strength: ~1500-1800 Elo

🚀 Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "SBellilty/llm-chess-agent-v3-half-training")

# Use with the official challenge environment
# See: https://github.com/AIcrowd/global-chess-challenge-2025-starter-kit

📝 Training

Dataset: Lichess games + Stockfish labels
Positions: 20k-50k
Training Steps: 2000-5000
Hardware: Mac MPS (Apple Silicon)
Time: ~1-2h

🏆 Challenge

Submitted to the Global Chess Challenge 2025:

https://www.aicrowd.com/challenges/global-chess-challenge-2025

📄 License

MIT License

🙏 Acknowledgments

Challenge organizers: AIcrowd & AGI House
Base model: Qwen team
Chess engine: Stockfish
Data source: Lichess Open Database

Downloads last month: 7

Safetensors

Model size

2B params

Tensor type

F16

Model tree for SBellilty/llm-chess-agent-v3-half-training

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Adapter

(992)

this model