Instructions to use clarkkitchen22/pokemon-red-commander-qwen3-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use clarkkitchen22/pokemon-red-commander-qwen3-4b with Transformers:

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

pipe = pipeline("text-generation", model="clarkkitchen22/pokemon-red-commander-qwen3-4b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("clarkkitchen22/pokemon-red-commander-qwen3-4b")
model = AutoModelForCausalLM.from_pretrained("clarkkitchen22/pokemon-red-commander-qwen3-4b")
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 clarkkitchen22/pokemon-red-commander-qwen3-4b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="clarkkitchen22/pokemon-red-commander-qwen3-4b",
	filename="pokemon-red-commander-Q4_K_M.gguf",
)

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use clarkkitchen22/pokemon-red-commander-qwen3-4b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M

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 clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M

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 clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M

Use Docker

docker model run hf.co/clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M

LM Studio
Jan

vLLM

How to use clarkkitchen22/pokemon-red-commander-qwen3-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "clarkkitchen22/pokemon-red-commander-qwen3-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "clarkkitchen22/pokemon-red-commander-qwen3-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M

SGLang

How to use clarkkitchen22/pokemon-red-commander-qwen3-4b 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 "clarkkitchen22/pokemon-red-commander-qwen3-4b" \
    --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": "clarkkitchen22/pokemon-red-commander-qwen3-4b",
		"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 "clarkkitchen22/pokemon-red-commander-qwen3-4b" \
        --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": "clarkkitchen22/pokemon-red-commander-qwen3-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use clarkkitchen22/pokemon-red-commander-qwen3-4b with Ollama:
```
ollama run hf.co/clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M
```

Unsloth Studio new

How to use clarkkitchen22/pokemon-red-commander-qwen3-4b 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 clarkkitchen22/pokemon-red-commander-qwen3-4b 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 clarkkitchen22/pokemon-red-commander-qwen3-4b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for clarkkitchen22/pokemon-red-commander-qwen3-4b to start chatting

Pi new

How to use clarkkitchen22/pokemon-red-commander-qwen3-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M

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": "clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use clarkkitchen22/pokemon-red-commander-qwen3-4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf clarkkitchen22/pokemon-red-commander-qwen3-4b: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 clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use clarkkitchen22/pokemon-red-commander-qwen3-4b with Docker Model Runner:
```
docker model run hf.co/clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M
```

Lemonade

How to use clarkkitchen22/pokemon-red-commander-qwen3-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull clarkkitchen22/pokemon-red-commander-qwen3-4b:Q4_K_M

Run and chat with the model

lemonade run user.pokemon-red-commander-qwen3-4b-Q4_K_M

List all available models

lemonade list

Pokemon Red Commander — Qwen3-4B

A fine-tuned Qwen3-4B model that serves as the Strategic Commander for an autonomous Pokemon Red playthrough. It analyzes game state and makes optimal decisions about battles, team building, routing, and item usage based on Gen 1 Pokemon mechanics.

Model Details

Property	Value
Base model	`Qwen/Qwen3-4B` (via `unsloth/Qwen3-4B-bnb-4bit`)
Parameters	4B (merged 16-bit)
Method	QLoRA (4-bit NormalFloat via bitsandbytes)
Framework	Unsloth + Hugging Face TRL
Chat format	ChatML (`<\|im_start\|>` / `<\|im_end\|>`)
Max sequence length	1024 tokens
Hardware	NVIDIA RTX 4090 (24 GB VRAM)
Training time	~15 minutes

LoRA Configuration

Parameter	Value
Rank (r)	16
Alpha	32
Dropout	0.05
Target modules	`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`

Training Hyperparameters

Parameter	Value
Epochs	3
Learning rate	2e-4
Optimizer	`paged_adamw_8bit`
LR scheduler	Cosine
Batch size	1 (per device)
Gradient accumulation	16 (effective batch = 16)
Warmup ratio	0.05
Weight decay	0.01
Precision	bf16
Gradient checkpointing	Enabled
Packing	Enabled

Training Results

Metric	Value
Initial training loss	4.37
Final training loss	0.22
Eval loss	0.3049

Dataset

Trained on 903 examples (53 validation, 48 test) covering 12 categories of Pokemon Red knowledge:

Pokedex knowledge, move knowledge, type matchups
Battle strategy, team building, gym strategy, Elite Four
Route planning, wild encounters, item usage
Leveling efficiency, game mechanics, speedrun tactics

Data sourced from PokeAPI (151 Gen 1 Pokemon, 165 moves, 225 type matchups, 78 evolutions) and formatted as instruction-following conversations.

Usage

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "clarkkitchen22/pokemon-red-commander-qwen3-4b",
    torch_dtype="auto",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(
    "clarkkitchen22/pokemon-red-commander-qwen3-4b"
)

messages = [
    {"role": "system", "content": "You are the Strategic Commander for a Pokemon Red autonomous playthrough."},
    {"role": "user", "content": "My Charizard (Lv 40, HP 98/130) is facing Misty's Starmie (Lv 21). I have Flamethrower, Slash, Fly, and Earthquake. What move should I use?"},
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.3, top_p=0.9)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))

With llama.cpp / Ollama (GGUF)

GGUF quantized versions are also available in this repo (see files).

# llama.cpp
./llama-cli -m pokemon-red-commander-Q4_K_M.gguf -p "<|im_start|>user\nWhat Pokemon should I use against Brock?<|im_end|>\n<|im_start|>assistant\n"

# Ollama
ollama run clarkkitchen22/pokemon-red-commander-qwen3-4b

Intended Use

This model is designed to be the decision-making brain for an autonomous Pokemon Red playthrough system. It pairs with:

A Game Boy emulator bridge that reads game state from memory
A RAG system for retrieving detailed Pokemon knowledge
A Telegram bot for remote monitoring and control

Limitations

Trained exclusively on Gen 1 (Pokemon Red/Blue) data — does not generalize to later generations
Small training set (903 examples) — may hallucinate on edge cases
Optimized for strategic decisions, not general conversation
4B parameter model — larger models will perform better on complex multi-step reasoning

License

Apache 2.0 (following the Qwen3 base model license)

Downloads last month: 130

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for clarkkitchen22/pokemon-red-commander-qwen3-4b

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

(221)

this model

Quantizations

2 models