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

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"])

@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},
}

@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}}
}