Instructions to use Lyte/QuadConnect2.5-0.5B-v0.0.9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lyte/QuadConnect2.5-0.5B-v0.0.9b with Transformers:

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

pipe = pipeline("text-generation", model="Lyte/QuadConnect2.5-0.5B-v0.0.9b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lyte/QuadConnect2.5-0.5B-v0.0.9b")
model = AutoModelForCausalLM.from_pretrained("Lyte/QuadConnect2.5-0.5B-v0.0.9b")
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]:]))

llama-cpp-python

How to use Lyte/QuadConnect2.5-0.5B-v0.0.9b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Lyte/QuadConnect2.5-0.5B-v0.0.9b",
	filename="unsloth.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Lyte/QuadConnect2.5-0.5B-v0.0.9b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0

Use Docker

docker model run hf.co/Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0

LM Studio
Jan

vLLM

How to use Lyte/QuadConnect2.5-0.5B-v0.0.9b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lyte/QuadConnect2.5-0.5B-v0.0.9b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lyte/QuadConnect2.5-0.5B-v0.0.9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0

SGLang

How to use Lyte/QuadConnect2.5-0.5B-v0.0.9b 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 "Lyte/QuadConnect2.5-0.5B-v0.0.9b" \
    --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": "Lyte/QuadConnect2.5-0.5B-v0.0.9b",
		"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 "Lyte/QuadConnect2.5-0.5B-v0.0.9b" \
        --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": "Lyte/QuadConnect2.5-0.5B-v0.0.9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Lyte/QuadConnect2.5-0.5B-v0.0.9b with Ollama:
```
ollama run hf.co/Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0
```

Unsloth Studio new

How to use Lyte/QuadConnect2.5-0.5B-v0.0.9b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Lyte/QuadConnect2.5-0.5B-v0.0.9b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Lyte/QuadConnect2.5-0.5B-v0.0.9b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Lyte/QuadConnect2.5-0.5B-v0.0.9b to start chatting

Pi new

How to use Lyte/QuadConnect2.5-0.5B-v0.0.9b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Lyte/QuadConnect2.5-0.5B-v0.0.9b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use Lyte/QuadConnect2.5-0.5B-v0.0.9b with Docker Model Runner:
```
docker model run hf.co/Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0
```

Lemonade

How to use Lyte/QuadConnect2.5-0.5B-v0.0.9b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Lyte/QuadConnect2.5-0.5B-v0.0.9b:Q8_0

Run and chat with the model

lemonade run user.QuadConnect2.5-0.5B-v0.0.9b-Q8_0

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

QuadConnect2.5-0.5B-v0.0.9b - A Strategic Connect Four AI

🎮 Overview

QuadConnect2.5-0.5B is a specialized language model trained to master the game of Connect Four. Built on Qwen 2.5 (0.5B parameter base), this model uses GRPO (Group Relative Policy Optimization) to learn the strategic intricacies of Connect Four gameplay.

Status: Early training experiments (v0.0.9b) - Reward functions still evolving

🔍 Model Details

Developed by: Lyte
Model type: Small Language Model (SLM)
Language: English
Base model: unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit
Training method: TRL's GRPO
Training data: Lyte/ConnectFour-T10

🚀 Quick Start

Option 1: Using Transformers

from transformers import pipeline

SYSTEM_PROMPT = """You are a master Connect Four strategist whose goal is to win while preventing your opponent from winning. The game is played on a 6x7 grid (columns a–g, rows 1–6 with 1 at the bottom) where pieces drop to the lowest available spot.

Board:
- Represented as a list of occupied cells in the format: <column><row>(<piece>), e.g., 'a1(O)'.
- For example: 'a1(O), a2(X), b1(O)' indicates that cell a1 has an O, a2 has an X, and b1 has an O.
- An empty board is shown as 'Empty Board'.
- Win by connecting 4 pieces in any direction (horizontal, vertical, or diagonal).

Strategy:
1. Identify taken positions, and empty positions.
2. Find and execute winning moves.
3. If There isn't a winning move, then block your opponent's potential wins.
4. Control the center and set up future moves.

Respond in XML:
<reasoning>
Explain your thought process, focusing on your winning move, how you block your opponent, and your strategic plans.
</reasoning>
<move>
Specify the column letter (a–g) for your next move.
</move>
"""

board = {
    "empty": "Game State:\n- You are playing as: X\n- Your previous moves: \n- Opponent's moves: \n- Current board state: Empty Board\n- Next available position per column:  \nColumn a: a1, a2, a3, a4, a5, a6  \nColumn b: b1, b2, b3, b4, b5, b6  \nColumn c: c1, c2, c3, c4, c5, c6  \nColumn d: d1, d2, d3, d4, d5, d6  \nColumn e: e1, e2, e3, e4, e5, e6  \nColumn f: f1, f2, f3, f4, f5, f6  \nColumn g: g1, g2, g3, g4, g5, g6\n\nMake your move.",
    "one_move": "Game State:\n- You are playing as: X\n- Your previous moves: \n- Opponent's moves: b1\n- Current board state: b1(O)\n- Next available position per column:  \nColumn a: a1, a2, a3, a4, a5, a6  \nColumn b: b2, b3, b4, b5, b6  \nColumn c: c1, c2, c3, c4, c5, c6  \nColumn d: d1, d2, d3, d4, d5, d6  \nColumn e: e1, e2, e3, e4, e5, e6  \nColumn f: f1, f2, f3, f4, f5, f6  \nColumn g: g1, g2, g3, g4, g5, g6\n\nMake your move.",
    "four_moves": "Game State:\n- You are playing as: X\n- Your previous moves: a1, a2\n- Opponent's moves: d1, a3\n- Current board state: a1(X), d1(O), a2(X), a3(O)\n- Next available position per column:  \nColumn a: a4, a5, a6  \nColumn b: b1, b2, b3, b4, b5, b6  \nColumn c: c1, c2, c3, c4, c5, c6  \nColumn d: d2, d3, d4, d5, d6  \nColumn e: e1, e2, e3, e4, e5, e6  \nColumn f: f1, f2, f3, f4, f5, f6  \nColumn g: g1, g2, g3, g4, g5, g6\n\nMake your move.",
}

generator = pipeline("text-generation", model="Lyte/QuadConnect2.5-0.5B-v0.0.9b", device="cuda")

# use 'empty', 'one_move' or 'four_moves' in board['']
output = generator([
    {"role": "system", "content": SYSTEM_PROMPT}, 
    {"role": "user", "content": board['empty']}
], max_new_tokens=10245, return_full_text=False)[0]

print(output["generated_text"])

Option 2: Using GGUF

Download the Quantized GGUF (Q8_0) and use it in your favorite GGUF inference engine (e.g., LMStudio).

Option 3: Using Hugging Face Space

Visit the QuadConnect Space to interact with the model directly. You can also duplicate the space or download its code for local use.

📊 Evaluation Results

Model performance was evaluated on the Lyte/ConnectFour-T10 validation split with various temperature settings.

Summary Metrics Comparison

Metric	v0.0.6b (Temp 0.6)	v0.0.8b (Temp 0.6)	v0.0.9b (Temp 0.6)	v0.0.9b (Temp 0.8)	v0.0.9b (Temp 1.0)
Total games evaluated	5082	5082	5082	5082	5082
Correct predictions	518	394	516	713	677
Accuracy	10.19%	7.75%	10.15%	14.03%	13.32%
Most common move	d (41.14%)	d (67.61%)	a (38.72%)	a (31.01%)	a (26.99%)
Middle column usage	75.05%	99.53%	29.08%	35.43%	39.49%

Move Distribution by Column

Column	v0.0.6b (Temp 0.6)	v0.0.8b (Temp 0.6)	v0.0.9b (Temp 0.6)	v0.0.9b (Temp 0.8)	v0.0.9b (Temp 1.0)
a	603 (19.02%)	3 (0.12%)	1447 (38.72%)	1547 (31.01%)	1351 (26.99%)
b	111 (3.50%)	4 (0.16%)	644 (17.23%)	924 (18.52%)	997 (19.92%)
c	785 (24.76%)	463 (17.96%)	648 (17.34%)	1003 (20.11%)	985 (19.68%)
d	1304 (41.14%)	1743 (67.61%)	101 (2.70%)	202 (4.05%)	306 (6.11%)
e	290 (9.15%)	360 (13.96%)	338 (9.04%)	562 (11.27%)	686 (13.70%)
f	50 (1.58%)	3 (0.12%)	310 (8.30%)	408 (8.18%)	354 (7.07%)
g	27 (0.85%)	2 (0.08%)	249 (6.66%)	342 (6.86%)	327 (6.53%)

🔧 Training Details

Data Preparation

Started with Leon-LLM/Connect-Four-Datasets-Collection
Filtered for clean, complete entries
Further filtered to include only games with 10 or fewer turns
Split into train and validation sets
Final dataset: Lyte/ConnectFour-T10

Evaluation Parameters

Temperature: 0.6, 0.8, 1.0 (compared)
Top-p: 0.95
Max tokens: 1024

Framework Versions

TRL: 0.15.1
Transformers: 4.49.0
PyTorch: 2.5.1+cu121
Datasets: 3.2.0
Tokenizers: 0.21.0

📚 Citations

For GRPO:

@article{zhihong2024deepseekmath,
    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
    year         = 2024,
    eprint       = {arXiv:2402.03300},
}

For TRL:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Downloads last month: 33

Safetensors

Model size

0.5B params

Tensor type

BF16

Model tree for Lyte/QuadConnect2.5-0.5B-v0.0.9b

Quantizations

2 models

Dataset used to train Lyte/QuadConnect2.5-0.5B-v0.0.9b

Space using Lyte/QuadConnect2.5-0.5B-v0.0.9b 1

Paper for Lyte/QuadConnect2.5-0.5B-v0.0.9b

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Paper • 2402.03300 • Published Feb 5, 2024 • 145