Instructions to use ldp72/Test-SmolLM-Marcel-codecarbon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ldp72/Test-SmolLM-Marcel-codecarbon with Transformers:

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

pipe = pipeline("text-generation", model="ldp72/Test-SmolLM-Marcel-codecarbon")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ldp72/Test-SmolLM-Marcel-codecarbon")
model = AutoModelForCausalLM.from_pretrained("ldp72/Test-SmolLM-Marcel-codecarbon")
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

vLLM

How to use ldp72/Test-SmolLM-Marcel-codecarbon with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ldp72/Test-SmolLM-Marcel-codecarbon"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ldp72/Test-SmolLM-Marcel-codecarbon",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ldp72/Test-SmolLM-Marcel-codecarbon

SGLang

How to use ldp72/Test-SmolLM-Marcel-codecarbon 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 "ldp72/Test-SmolLM-Marcel-codecarbon" \
    --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": "ldp72/Test-SmolLM-Marcel-codecarbon",
		"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 "ldp72/Test-SmolLM-Marcel-codecarbon" \
        --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": "ldp72/Test-SmolLM-Marcel-codecarbon",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ldp72/Test-SmolLM-Marcel-codecarbon with Docker Model Runner:
```
docker model run hf.co/ldp72/Test-SmolLM-Marcel-codecarbon
```

Test-SmolLM-Marcel-codecarbon

File size: 1,291 Bytes

8d658b6
d979620

timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
2025-08-28T15:49:53,lm_adaptation,ef663567-f656-4a5f-addc-c59c4af2a2ec,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,305.22420004196465,0.0004140588578183,1.3565728332203015e-06,2.548125,33.58575069944228,54.0,0.0006163177559056,0.0031272630573653,0.0036451816167925,0.0073887624300634,France,FRA,,,,Linux-5.10.0-32-amd64-x86_64-with-glibc2.35,3.12.11,3.0.4,32,AMD EPYC 7282 16-Core Processor,1,1 x NVIDIA A100-PCIE-40GB,2.3387,48.8582,503.433219909668,process,N,1.0
2025-08-28T16:18:26,lm_adaptation,6a99e4c0-615f-4ac7-b8b9-fbb41b6953bf,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,339.06427432689816,0.00047581583856711547,1.4033204751862846e-06,2.95375,34.202068769585054,62.0,0.0006691973303178071,0.003499830022064998,0.004321770816162591,0.008490798168545395,France,FRA,,,,Linux-5.10.0-32-amd64-x86_64-with-glibc2.35,3.12.11,3.0.4,32,AMD EPYC 7282 16-Core Processor,1,1 x NVIDIA A100-PCIE-40GB,2.3387,48.8582,503.43321990966797,process,N,1.0