Instructions to use anakin87/LFM2-2.6B-mr-tictactoe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anakin87/LFM2-2.6B-mr-tictactoe with Transformers:

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

pipe = pipeline("text-generation", model="anakin87/LFM2-2.6B-mr-tictactoe")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anakin87/LFM2-2.6B-mr-tictactoe")
model = AutoModelForCausalLM.from_pretrained("anakin87/LFM2-2.6B-mr-tictactoe", 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 anakin87/LFM2-2.6B-mr-tictactoe with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anakin87/LFM2-2.6B-mr-tictactoe"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anakin87/LFM2-2.6B-mr-tictactoe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anakin87/LFM2-2.6B-mr-tictactoe

SGLang

How to use anakin87/LFM2-2.6B-mr-tictactoe 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 "anakin87/LFM2-2.6B-mr-tictactoe" \
    --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": "anakin87/LFM2-2.6B-mr-tictactoe",
		"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 "anakin87/LFM2-2.6B-mr-tictactoe" \
        --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": "anakin87/LFM2-2.6B-mr-tictactoe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use anakin87/LFM2-2.6B-mr-tictactoe with Docker Model Runner:
```
docker model run hf.co/anakin87/LFM2-2.6B-mr-tictactoe
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LFM2-2.6B-mr-tictactoe

A 2.6B parameter model that plays near-perfect Tic Tac Toe, outperforming openai/gpt-5-mini on this task.

Built from LiquidAI/LFM2-2.6B through a full training pipeline: Supervised Fine-Tuning on synthetic data, followed by two rounds of Reinforcement Learning (CISPO) in a verifiable Tic Tac Toe environment.

This model was developed as part of 🎓 LLM RL Environments Lil Course, a hands-on course on building RL environments for Language Models, where models learn from rewards, not examples. It walks through the full process of turning a small open model into a specialist that outperforms a large proprietary one on a specific task (Tic Tac Toe).

🤗🕹️ Play against Mr. Tic Tac Toe

Training pipeline

Step	Model	Method
1. SFT warm-up	anakin87/LFM2-2.6B-ttt-sft	SFT on 174 synthetic games from `gpt-5-mini`
2. RL round 1	anakin87/LFM2-2.6B-ttt-rl + merged	CISPO, 600 steps, opponents at 20-70% random
3. RL round 2	anakin87/LFM2-2.6B-ttt-rl-2 + this model	CISPO, 400 steps, opponents at 0-25% random, temp 1.25

Evaluation

100 games per setting. The model plays as X (first mover) against a Minimax-based opponent.

Model vs random opponent	% Wins	% Draws	% Losses	% Follows format	% Games w invalid moves
openai/gpt-5-mini	90	9	1	100	0
LiquidAI/LFM2-2.6B	40	11	49	27.8	40
anakin87/LFM2-2.6B-mr-tictactoe	90	10	0	100	0

Model vs optimal opponent	% Wins	% Draws	% Losses	% Follows format	% Games w invalid moves
openai/gpt-5-mini	0	76	24	100	0
LiquidAI/LFM2-2.6B	0	11	89	24.7	43
anakin87/LFM2-2.6B-mr-tictactoe	0	97	3	99.8	0