Poker & Blackjack Vision AI โ€” Gemma 4 26B-A4B LoRA

Fine-tuned Gemma 4 26B-A4B (vision MoE: 26B total params, 4B active per token) for poker and blackjack decision-making.

What This Model Does

Given a poker or blackjack game state, the model outputs the optimal action (fold, call, raise, hit, stand, etc.) as JSON.

This is a vision model โ€” it can process card images directly, enabling camera-to-decision pipelines (e.g., smart glasses โ†’ see cards โ†’ optimal play).

Training Details

  • Base model: unsloth/gemma-4-26B-A4B-it (MoE with vision encoder)
  • Method: LoRA (r=16, alpha=32) on q/k/v/o/gate/up/down projections
  • Data: 12,848 examples (3,072 poker + 9,776 blackjack)
    • Poker: Winning decisions from TAGBot, EquityBot, ExploitBot
    • Blackjack: Counter (I18) optimal strategy
  • Training: 3 epochs, 2,289 steps on NVIDIA A6000 48GB
  • Final metrics: Loss 0.109, Token accuracy 95.95%
  • Cost: ~$3.73 on RunPod

Poker Prompt Format

You are a specialist in playing 6-handed No Limit Texas Holdem. Do not explain your answer.

Game summary:
- Small blind: 5 chips, Big blind: 10 chips
- Your position: BTN, Your holding: As Ks
- Board: 7c 4d 2h
- Pot: 75, To call: 0, Your stack: 970
- Equity: 73%, Pot odds: 0%
- Legal actions: check, raise, all_in

Respond with ONLY valid JSON: {"action": "fold|check|call|raise|all_in", "amount": 0}

Blackjack Prompt Format

You are a blackjack expert. Decide the best action.
Your cards: Ace, 6 (total: 17 soft)
Dealer showing: 9
Available actions: hit, stand, double
Respond with ONLY the action word.

Usage with llama.cpp (recommended for Mac)

# Merge LoRA โ†’ GGUF Q3_K_M (~11GB, fits 16GB Mac)
# Then serve:
llama-server --model gemma4-poker-26b-q3_k_m.gguf --port 8080 --n-gpu-layers 999 --ctx-size 2048 --jinja

Important: Disable thinking mode for fast responses:

{"chat_template_kwargs": {"enable_thinking": false}}

Arena Results (E4B version, 1000 hands)

Metric Value
BB/100 -0.1 (breakeven)
VPIP 80.5%
Style LAG (loose-aggressive)
vs CallingStation +9.3 bb/100

Note: Model plays too many hands (VPIP too high). GRPO reinforcement learning is the planned fix.

Part of the Flywheel

This model is part of an iterative training loop:

  1. Bots play โ†’ generate winning decisions โ†’ SFT training (this model)
  2. Model plays in arena โ†’ find weaknesses โ†’ GRPO with reward functions
  3. Retrain โ†’ better model โ†’ repeat

Links

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for waltgrace/poker-gemma4-26b-a4b-lora

Adapter
(32)
this model