Instructions to use distil-labs/distil-qwen3.5-4b-invoice-decision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use distil-labs/distil-qwen3.5-4b-invoice-decision with Transformers:

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

pipe = pipeline("text-generation", model="distil-labs/distil-qwen3.5-4b-invoice-decision")
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("distil-labs/distil-qwen3.5-4b-invoice-decision")
model = AutoModelForCausalLM.from_pretrained("distil-labs/distil-qwen3.5-4b-invoice-decision", 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

vLLM

How to use distil-labs/distil-qwen3.5-4b-invoice-decision with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "distil-labs/distil-qwen3.5-4b-invoice-decision"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "distil-labs/distil-qwen3.5-4b-invoice-decision",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/distil-labs/distil-qwen3.5-4b-invoice-decision

SGLang

How to use distil-labs/distil-qwen3.5-4b-invoice-decision 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 "distil-labs/distil-qwen3.5-4b-invoice-decision" \
    --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": "distil-labs/distil-qwen3.5-4b-invoice-decision",
		"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 "distil-labs/distil-qwen3.5-4b-invoice-decision" \
        --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": "distil-labs/distil-qwen3.5-4b-invoice-decision",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use distil-labs/distil-qwen3.5-4b-invoice-decision with Docker Model Runner:
```
docker model run hf.co/distil-labs/distil-qwen3.5-4b-invoice-decision
```

distillabs commited on 17 days ago

Commit

938069d

verified ·

1 Parent(s): e419b0f

Correct reasoning length: median 272.5 tokens (tokenizer count)

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -39,7 +39,7 @@ How it was scored, all baselines, and the raw outputs: [https://github.com/disti
 ## How to use it
-The model was trained to reason before it answers, in a short fixed format (the checks in policy order, one line per invoice line, a running sum, stop at the first failure; about 160 tokens). Serve it with thinking on: `chat_template_kwargs: {"enable_thinking": true}`. The answer follows the reasoning.
 Serve it behind an OpenAI-compatible endpoint:

 ## How to use it
+The model was trained to reason before it answers, in a short fixed format (the checks in policy order, one line per invoice line, a running sum, stop at the first failure; median 272.5 tokens on the test set). Serve it with thinking on: `chat_template_kwargs: {"enable_thinking": true}`. The answer follows the reasoning.
 Serve it behind an OpenAI-compatible endpoint: