Instructions to use adikuma/mumble-cleanup with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adikuma/mumble-cleanup with Transformers:

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

pipe = pipeline("text-generation", model="adikuma/mumble-cleanup")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("adikuma/mumble-cleanup")
model = AutoModelForMultimodalLM.from_pretrained("adikuma/mumble-cleanup")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use adikuma/mumble-cleanup with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/adikuma/mumble-cleanup

SGLang

How to use adikuma/mumble-cleanup 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 "adikuma/mumble-cleanup" \
    --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": "adikuma/mumble-cleanup",
		"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 "adikuma/mumble-cleanup" \
        --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": "adikuma/mumble-cleanup",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adikuma/mumble-cleanup with Docker Model Runner:
```
docker model run hf.co/adikuma/mumble-cleanup
```

mumble-cleanup / src /cleanup /export /quantize.py

adikuma

initial upload: cleanup code and 688-pair seed dataset

fd0b01f verified 13 days ago

raw

history blame contribute delete

755 Bytes

	# dynamic int8 quantize the onnx via ort. dynamic (not static) because we do
	# not have a calibration dataset and dynamic works well for decoder-style LMs.

	from pathlib import Path


	def quantize_int8(fp32_onnx: Path, out_dir: Path) -> Path:
	from onnxruntime.quantization import quantize_dynamic, QuantType

	fp32_onnx = Path(fp32_onnx)
	out_dir = Path(out_dir)
	out_dir.mkdir(parents=True, exist_ok=True)
	int8_path = out_dir / "model.onnx"
	print(f"[quantize] {fp32_onnx} -> {int8_path}")
	quantize_dynamic(
	model_input=str(fp32_onnx),
	model_output=str(int8_path),
	weight_type=QuantType.QInt8,
	)
	print(f"[quantize] wrote {int8_path} ({int8_path.stat().st_size / 1e6:.1f} MB)")
	return int8_path