Instructions to use pcuenq/SmolLM3-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pcuenq/SmolLM3-3B with Transformers:

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

pipe = pipeline("text-generation", model="pcuenq/SmolLM3-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pcuenq/SmolLM3-3B")
model = AutoModelForCausalLM.from_pretrained("pcuenq/SmolLM3-3B")
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 pcuenq/SmolLM3-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pcuenq/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": "pcuenq/SmolLM3-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pcuenq/SmolLM3-3B

SGLang

How to use pcuenq/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 "pcuenq/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": "pcuenq/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 "pcuenq/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": "pcuenq/SmolLM3-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pcuenq/SmolLM3-3B with Docker Model Runner:
```
docker model run hf.co/pcuenq/SmolLM3-3B
```

Add response_template for streaming response parsing

by pcuenq HF Staff - opened 16 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+28

-1

Files changed (1) hide show

tokenizer_config.json +28 -1

tokenizer_config.json CHANGED Viewed

@@ -2060,5 +2060,32 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|im_end|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
 }

   ],
   "model_max_length": 131072,
   "pad_token": "<|im_end|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "response_template": {
+    "defaults": {
+      "role": "assistant"
+    },
+    "start_anchor": "<|im_start|>assistant\n",
+    "fields": {
+      "thinking": {
+        "open": "<think>",
+        "close": "</think>",
+        "content": "text"
+      },
+      "tool_calls": {
+        "open": "<tool_call>",
+        "close": "</tool_call>",
+        "repeats": true,
+        "content": "json",
+        "transform": {
+          "type": "function",
+          "function": "{content}"
+        }
+      },
+      "content": {
+        "close": "<|im_end|>",
+        "content": "text"
+      }
+    }
+  }
 }