Instructions to use SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr with Transformers:

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

pipe = pipeline("text-generation", model="SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr")
model = AutoModelForCausalLM.from_pretrained("SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr

SGLang

How to use SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr 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 "SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr" \
    --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": "SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr",
		"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 "SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr" \
        --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": "SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr with Docker Model Runner:
```
docker model run hf.co/SamsungSAILMontreal/Qwen3-4B-Instruct-2507-Fr
```

bknyaz commited on Feb 3

Commit

4098172

verified ·

1 Parent(s): 8997caf

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -80,8 +80,8 @@ To evaluate on gsm8k-fr you can use my fork https://github.com/bknyaz/lm-evaluat
 | Model                            | gsm8k  | french | gsm8k-fr | avg   |
 |----------------------------------|--------|--------|----------|-------|
-| Qwen3-1.4B-Instruct-2507         | 80.4   | 43.1   | 66.0     | 63.2  |
-| Qwen3-1.4B-Instruct-2507-Fr      | 72.3   | 45.7   | 60.7     | 59.6  |
 ## License

 | Model                            | gsm8k  | french | gsm8k-fr | avg   |
 |----------------------------------|--------|--------|----------|-------|
+| Qwen3-4B-Instruct-2507           | 80.4   | 43.1   | 66.0     | 63.2  |
+| Qwen3-4B-Instruct-2507-Fr        | 72.3   | 45.7   | 60.7     | 59.6  |
 ## License