Instructions to use oaimli/smollm3_3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oaimli/smollm3_3b with Transformers:

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

pipe = pipeline("text-generation", model="oaimli/smollm3_3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("oaimli/smollm3_3b")
model = AutoModelForCausalLM.from_pretrained("oaimli/smollm3_3b", 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 oaimli/smollm3_3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oaimli/smollm3_3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oaimli/smollm3_3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/oaimli/smollm3_3b

SGLang

How to use oaimli/smollm3_3b 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 "oaimli/smollm3_3b" \
    --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": "oaimli/smollm3_3b",
		"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 "oaimli/smollm3_3b" \
        --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": "oaimli/smollm3_3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use oaimli/smollm3_3b with Docker Model Runner:
```
docker model run hf.co/oaimli/smollm3_3b
```

oaimli commited on Nov 11, 2025

Commit

b2c384d

verified ·

1 Parent(s): e913a85

Update config.json

Browse files

add the rope scaling

Files changed (1) hide show

config.json +6 -2

config.json CHANGED Viewed

@@ -49,7 +49,7 @@
     "full_attention",
     "full_attention"
   ],
-  "max_position_embeddings": 65536,
   "max_window_layers": 28,
   "mlp_bias": false,
   "model_type": "smollm3",
@@ -98,7 +98,11 @@
   "pad_token_id": 128004,
   "pretraining_tp": 2,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
   "rope_theta": 5000000.0,
   "sliding_window": null,
   "transformers_version": "4.57.0",

     "full_attention",
     "full_attention"
   ],
+  "max_position_embeddings": 131072,
   "max_window_layers": 28,
   "mlp_bias": false,
   "model_type": "smollm3",
   "pad_token_id": 128004,
   "pretraining_tp": 2,
   "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "type": "yarn",
+    "factor": 2.0,
+    "original_max_position_embeddings": 65536
+  },
   "rope_theta": 5000000.0,
   "sliding_window": null,
   "transformers_version": "4.57.0",