Instructions to use pierretokns/qwen-0.5b-ccmcp-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pierretokns/qwen-0.5b-ccmcp-v2 with Transformers:

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

pipe = pipeline("text-generation", model="pierretokns/qwen-0.5b-ccmcp-v2")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("pierretokns/qwen-0.5b-ccmcp-v2", device_map="auto")

MLX

How to use pierretokns/qwen-0.5b-ccmcp-v2 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("pierretokns/qwen-0.5b-ccmcp-v2")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use pierretokns/qwen-0.5b-ccmcp-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pierretokns/qwen-0.5b-ccmcp-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pierretokns/qwen-0.5b-ccmcp-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pierretokns/qwen-0.5b-ccmcp-v2

SGLang

How to use pierretokns/qwen-0.5b-ccmcp-v2 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 "pierretokns/qwen-0.5b-ccmcp-v2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pierretokns/qwen-0.5b-ccmcp-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "pierretokns/qwen-0.5b-ccmcp-v2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pierretokns/qwen-0.5b-ccmcp-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use pierretokns/qwen-0.5b-ccmcp-v2 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "pierretokns/qwen-0.5b-ccmcp-v2" --prompt "Once upon a time"

Docker Model Runner
How to use pierretokns/qwen-0.5b-ccmcp-v2 with Docker Model Runner:
```
docker model run hf.co/pierretokns/qwen-0.5b-ccmcp-v2
```

qwen-0.5b-ccmcp-v2

Qwen 0.5B trained for Claude Chrome MCP tool calling (extended)

Attribution: Built with Qwen

Model Description

Fine-tuned for MCP (Model Context Protocol) tool calling with the Claude Chrome extension. The model generates tool calls for browser automation tasks.

Training Details

Base Model: Qwen/Qwen2.5-Coder-0.5B-Instruct
Method: LoRA fine-tuning on Apple Silicon (MLX)
Dataset: 1,782 MCP browser automation examples
Validation Loss: 0.077
Iterations: 2000
Naming Convention: {base}-{size}-ccmcp-{version}
- ccmcp = Claude Chrome MCP

Files

adapters.safetensors - LoRA adapter weights
adapter_config.json - LoRA configuration
qwen-0.5b-ccmcp-v2-f16.gguf - GGUF F16 format for llama.cpp/Ollama
checkpoints/ - Training checkpoints

Usage

With MLX (Apple Silicon)

from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler

model, tokenizer = load(
    "mlx-community/Qwen2.5-Coder-0.5B-Instruct-4bit",
    adapter_path="pierretokns/qwen-0.5b-ccmcp-v2"
)

messages = [
    {"role": "system", "content": "You are a browser automation assistant with MCP tools."},
    {"role": "user", "content": "Go to google.com"}
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
sampler = make_sampler(temp=0.1)

response = generate(model, tokenizer, prompt=prompt, max_tokens=150, sampler=sampler)
print(response)

With Ollama

# Download GGUF from this repo
# Create Modelfile:
cat > Modelfile << 'EOF'
FROM ./qwen-0.5b-ccmcp-v2-f16.gguf
PARAMETER num_ctx 8192
PARAMETER temperature 0.1
SYSTEM "You are a browser automation assistant with MCP tools."
EOF

# Create and run
ollama create qwen-0.5b-ccmcp-v2 -f Modelfile
ollama run qwen-0.5b-ccmcp-v2 "Go to google.com"

With Claude Code + Ollama

ANTHROPIC_BASE_URL=http://localhost:11434 \
ANTHROPIC_AUTH_TOKEN=ollama \
ANTHROPIC_API_KEY=ollama \
claude --model qwen-0.5b-ccmcp-v2

MCP Tools

The model was trained on 16 MCP browser automation tools: navigate, read_page, find, computer, form_input, get_page_text, screenshot, javascript_tool, tabs_context_mcp, tabs_create_mcp, gif_creator, upload_image, read_console_messages, read_network_requests, shortcuts_list, shortcuts_execute

License

This model is licensed under the Apache 2.0 License.

Downloads last month: -; Downloads are not tracked for this model. How to track

MLX

Hardware compatibility

Quantized

Model tree for pierretokns/qwen-0.5b-ccmcp-v2

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-Coder-0.5B

Finetuned

Qwen/Qwen2.5-Coder-0.5B-Instruct

Adapter

(52)

this model