Instructions to use predbrad/Genaro-poker-1.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use predbrad/Genaro-poker-1.7B with Transformers:

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

pipe = pipeline("text-generation", model="predbrad/Genaro-poker-1.7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("predbrad/Genaro-poker-1.7B")
model = AutoModelForCausalLM.from_pretrained("predbrad/Genaro-poker-1.7B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use predbrad/Genaro-poker-1.7B with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf predbrad/Genaro-poker-1.7B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf predbrad/Genaro-poker-1.7B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf predbrad/Genaro-poker-1.7B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf predbrad/Genaro-poker-1.7B:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf predbrad/Genaro-poker-1.7B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf predbrad/Genaro-poker-1.7B:Q4_K_M

Use Docker

docker model run hf.co/predbrad/Genaro-poker-1.7B:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use predbrad/Genaro-poker-1.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "predbrad/Genaro-poker-1.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "predbrad/Genaro-poker-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/predbrad/Genaro-poker-1.7B:Q4_K_M

SGLang

How to use predbrad/Genaro-poker-1.7B 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 "predbrad/Genaro-poker-1.7B" \
    --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": "predbrad/Genaro-poker-1.7B",
		"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 "predbrad/Genaro-poker-1.7B" \
        --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": "predbrad/Genaro-poker-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use predbrad/Genaro-poker-1.7B with Ollama:
```
ollama run hf.co/predbrad/Genaro-poker-1.7B:Q4_K_M
```
Unsloth Desktop

How to use predbrad/Genaro-poker-1.7B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf predbrad/Genaro-poker-1.7B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "predbrad/Genaro-poker-1.7B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use predbrad/Genaro-poker-1.7B with Docker Model Runner:
```
docker model run hf.co/predbrad/Genaro-poker-1.7B:Q4_K_M
```

Lemonade

How to use predbrad/Genaro-poker-1.7B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull predbrad/Genaro-poker-1.7B:Q4_K_M

Run and chat with the model

lemonade run user.Genaro-poker-1.7B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use predbrad/Genaro-poker-1.7B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf predbrad/Genaro-poker-1.7B:Q4_K_M

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 predbrad/Genaro-poker-1.7B:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use predbrad/Genaro-poker-1.7B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf predbrad/Genaro-poker-1.7B:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "predbrad/Genaro-poker-1.7B:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

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

Genaro Poker 1.7B

A phone-sized poker player. Genaro is a full fine-tune of Qwen3-1.7B built to be the opponents in PokerSI, an Android poker game where every seat is a small language model running on the phone with llama.cpp. It is the bigger, sharper sibling of Genaro Poker 0.6B, for phones with 6 GB+ of RAM.

Given PokerSI's prompt for one decision (a persona, the rules, what the seat can see, the legal moves), Genaro answers with one JSON object: a sound, legal move and, on talk turns, a short line in the character's voice, trained not to give its cards away.

{"action": "call", "amount": 55, "say": "The pot looks like it's brewing a little sunshine."}
{"action": "check", "amount": 0, "say": "Ahoy, these doubloons are worth a fortune!"}
{"action": "raise", "amount": 240, "say": "Get those reps in, I see potential!"}

File	Use
`genaro-poker-1.7b-Q4_K_M.gguf` (1.1 GB)	On-device / llama.cpp. What PokerSI downloads. Chat template embedded.
`model.safetensors` + config/tokenizer (bf16)	transformers, further fine-tuning, other quantizations

Smaller, faster sibling for any phone: predbrad/Genaro-poker. Code, data pipeline and evals: github.com/bradflaugher/genaro-poker. Training data: predbrad/genaro-poker-sft.

Results

600 held-out PokerSI decisions over all six variants (Texas Hold'em, Omaha, Five-Card Draw, Seven-Card Stud, Short Deck, Crazy Pineapple). Every model runs through llama.cpp exactly as the app runs it: same prompt, GBNF grammar and sampling (persona temperature 0.6-0.9, top-k 40, top-p 0.95, max 96 tokens).

model	GGUF	agreement	blunders /100	leaks	card talk	repeats	>12 words	live play bb/100
Qwen3 1.7B (base)	1282 MB	39.7%	8.2	17.9%	49.7%	8.2%	48.3%	—
LFM2.5 1.2B (PokerSI's previous default)	731 MB	55.8%	12.6	2.6%	29.8%	8.5%	9.4%	-80 ± 80
Genaro Poker 0.6B	397 MB	78.5%	9.1	0.0%	0.3%	0.0%	0.0%	-84 ± 52
Genaro Poker 1.7B	1107 MB	80.2%	7.5	0.3%	0.9%	0.6%	0.0%	-45 ± 64

Agreement: same move as the majority of 9 House Bot teachers. Blunder: folding with equity ≥ 10 points above the pot odds, or calling/raising with equity ≥ 15 points below them (bluffs by bluffing personas excepted). Leak: a line PokerSI's own HandBlur would censor. Card talk: any card, rank or hand word at all. Live play and every other model: results.

Use

In PokerSI: MODELS → Genaro Poker 1.7B → download. That's it.

llama.cpp: PokerSI-style messages, with a grammar and thinking off:

llama-server -m genaro-poker-1.7b-Q4_K_M.gguf --jinja -c 4096

The prompt format is PokerSI's (llm/PokerPrompt.kt); real examples are in the dataset. Outside that format Genaro is just a small, poker-obsessed Qwen3; it is not a general chat model.

transformers:

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("predbrad/Genaro-poker-1.7B")
model = AutoModelForCausalLM.from_pretrained("predbrad/Genaro-poker", dtype="auto")
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)

Training

Prompts: 33k self-play hands of PokerSI's own Kotlin engine and prompt builder, compiled into a bridge, so every prompt is byte-for-byte what the app sends.
Moves: the majority of 9 House Bot teachers (PokerSI's heuristic, each with the persona's style and 1,000-sample Monte Carlo equity).
Table talk: written by Gemma 4 E4B for the chosen move, kept only if it passes the grammar's rules, 2-12 words, no card or hand vocabulary, PokerSI's repeat rules and PokerSI's HandBlur. Quiet turns have no line, like the app's quiet-turn grammar.
Recipe: 22,941 conversations, full fine-tune, bf16, 2 epochs, lr 3e-5 cosine, effective batch 64, loss on the reply only. ~2 h on one NVIDIA RTX Spark N1X laptop. See training_config.yaml.

Limits

Genaro imitates PokerSI's House Bot. That makes it a reasonable, readable game-night opponent, not a strong poker player; in live play it does not beat House Bots.
Trained only for PokerSI's prompt format, in English.
Lines are family-friendly by construction; personas come from PokerSI.

License

Apache 2.0, inherited from Qwen3-1.7B. Training data was generated with PokerSI (MIT) and Gemma 4 (Apache 2.0).

Downloads last month: 270

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for predbrad/Genaro-poker-1.7B

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Finetuned

(1357)

this model

Quantizations

1 model

predbrad
/

Genaro-poker-1.7B

Genaro Poker 1.7B

Results

Use

Training

Limits

License

Model tree for predbrad/Genaro-poker-1.7B

Dataset used to train predbrad/Genaro-poker-1.7B