Instructions to use mainbrains/SmolLM2-1.7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mainbrains/SmolLM2-1.7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="mainbrains/SmolLM2-1.7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mainbrains/SmolLM2-1.7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("mainbrains/SmolLM2-1.7B-Instruct", 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]:]))

Transformers.js

How to use mainbrains/SmolLM2-1.7B-Instruct with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('text-generation', 'mainbrains/SmolLM2-1.7B-Instruct');

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mainbrains/SmolLM2-1.7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mainbrains/SmolLM2-1.7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mainbrains/SmolLM2-1.7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mainbrains/SmolLM2-1.7B-Instruct

SGLang

How to use mainbrains/SmolLM2-1.7B-Instruct 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 "mainbrains/SmolLM2-1.7B-Instruct" \
    --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": "mainbrains/SmolLM2-1.7B-Instruct",
		"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 "mainbrains/SmolLM2-1.7B-Instruct" \
        --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": "mainbrains/SmolLM2-1.7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mainbrains/SmolLM2-1.7B-Instruct with Docker Model Runner:
```
docker model run hf.co/mainbrains/SmolLM2-1.7B-Instruct
```

mainbrains commited on 1 day ago

Commit

8187e5e

verified ·

1 Parent(s): 36b1407

Add maintainer notes and deployment config

Browse files

Files changed (1) hide show

README.md +9 -0

README.md CHANGED Viewed

@@ -13,6 +13,15 @@ base_model:
 ---
 # SmolLM2
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61c141342aac764ce1654e43/y45hIMNREW7w_XpHYB_0q.png)

 ---
+> **Fork maintained by [@mainbrains](https://huggingface.co/mainbrains)** — Evaluating SmolLM2 for ultra-lightweight edge deployment. GGUF quantizations and benchmarks on constrained hardware.
+>
+> **Target:** Sub-1W inference on Raspberry Pi 5 for always-on automation agents. Q4_K_M runs at ~15 tok/s with 1.2GB RAM.
+---
 # SmolLM2
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61c141342aac764ce1654e43/y45hIMNREW7w_XpHYB_0q.png)