Instructions to use GL3MON/Qwen3.5-2B-chess-rl-grpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GL3MON/Qwen3.5-2B-chess-rl-grpo with Transformers:

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

pipe = pipeline("text-generation", model="GL3MON/Qwen3.5-2B-chess-rl-grpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GL3MON/Qwen3.5-2B-chess-rl-grpo")
model = AutoModelForCausalLM.from_pretrained("GL3MON/Qwen3.5-2B-chess-rl-grpo", device_map="auto")
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 Settings

vLLM

How to use GL3MON/Qwen3.5-2B-chess-rl-grpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GL3MON/Qwen3.5-2B-chess-rl-grpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GL3MON/Qwen3.5-2B-chess-rl-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GL3MON/Qwen3.5-2B-chess-rl-grpo

SGLang

How to use GL3MON/Qwen3.5-2B-chess-rl-grpo 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 "GL3MON/Qwen3.5-2B-chess-rl-grpo" \
    --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": "GL3MON/Qwen3.5-2B-chess-rl-grpo",
		"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 "GL3MON/Qwen3.5-2B-chess-rl-grpo" \
        --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": "GL3MON/Qwen3.5-2B-chess-rl-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GL3MON/Qwen3.5-2B-chess-rl-grpo with Docker Model Runner:
```
docker model run hf.co/GL3MON/Qwen3.5-2B-chess-rl-grpo
```

Qwen-3.5-2B Chess RL (GRPO)

Overview

This is a fine-tuned version of Qwen-3.5-2B on chess move prediction using Group Relative Policy Optimization (GRPO) with Stockfish as the reward signal. This is an RL fine-tuned model that builds upon the SFT checkpoint.

Model Details

Base Model: Qwen/Qwen3.5-2B (SFT checkpoint: checkpoint-5940)
RL Method: Group Relative Policy Optimization (GRPO)
Reward Signal: Stockfish (depth=10, 1 thread)
Sequence Length: 1024 tokens
Precision: bfloat16

GRPO Hyperparameters

Parameter	Value
Beta (KL control)	0.1
Epsilon (clip range)	0.2
Learning Rate	1e-6
Samples per prompt	4
Epochs	1

Training Configuration

SFT Pre-training

Learning Rate: 1e-5
Batch Size: 4 (per device)
Epochs: 3
Scheduler: Cosine with 100 warmup steps

RL Fine-tuning (GRPO)

Learning Rate: 1e-6
Batch Size: 2 (per device)
Gradient Accumulation: 2
Max Steps: 2500
Logging Steps: 10
Save Steps: 500

Dataset

The RL training was performed on a split of the ChessInstruct dataset with the following task categories:

FIND_NEXT_BEST_MOVE
FIND_ADVANTAGED_PLAYER
FIND_FINAL_SCORE
MLM_ON_MOVES
FIND_LAST_MOVE
SORT_FENS

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "GL3MON/Qwen3.5-2B-chess-rl-grpo"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Example: Generate chess moves
messages = [
    {"role": "system", "content": "You are a chess assistant. Provide the best move in SAN format."},
    {"role": "user", "content": "What is the best move for white in the position: rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - 0 1?"}
]

input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
outputs = model.generate(input_ids, max_new_tokens=50, temperature=0.7, do_sample=True)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Training Pipeline

Step 1: SFT - First trained on ChessInstruct using Supervised Fine-Tuning
Step 2: RL - Further fine-tuned using GRPO with Stockfish reward

License

MIT License

Citation

@software{ChessLM2026,
  title = {ChessLM - Qwen-3.5-2B Chess Assistant (RL GRPO)},
  author = {GL3MON},
  year = {2026},
  url = {https://huggingface.co/GL3MON/Qwen3.5-2B-chess-rl-grpo}
}