Instructions to use wayne377/SmolLM3-3B-SFT-WebShop with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wayne377/SmolLM3-3B-SFT-WebShop with Transformers:

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

pipe = pipeline("text-generation", model="wayne377/SmolLM3-3B-SFT-WebShop")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wayne377/SmolLM3-3B-SFT-WebShop")
model = AutoModelForCausalLM.from_pretrained("wayne377/SmolLM3-3B-SFT-WebShop", 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 wayne377/SmolLM3-3B-SFT-WebShop with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wayne377/SmolLM3-3B-SFT-WebShop"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wayne377/SmolLM3-3B-SFT-WebShop",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wayne377/SmolLM3-3B-SFT-WebShop

SGLang

How to use wayne377/SmolLM3-3B-SFT-WebShop 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 "wayne377/SmolLM3-3B-SFT-WebShop" \
    --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": "wayne377/SmolLM3-3B-SFT-WebShop",
		"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 "wayne377/SmolLM3-3B-SFT-WebShop" \
        --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": "wayne377/SmolLM3-3B-SFT-WebShop",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wayne377/SmolLM3-3B-SFT-WebShop with Docker Model Runner:
```
docker model run hf.co/wayne377/SmolLM3-3B-SFT-WebShop
```

SmolLM3-3B-SFT-WebShop


Task	WebShop
Stage	SFT (behavior-cloning) initialization
Base	`HuggingFaceTB/SmolLM3-3B`
Init for this run	`models/smollm3-3b-agent`
Source checkpoint	`rl/ckpts/ws_sft_div_smollm3-3b/global_step_155` (global_step 155)
Format	bf16 safetensors, merged from hf-dir fp32 -> bf16 cast (per-tensor, login node)
Params	3,337,766,912
Weight drift vs. init (mean rel-L2)	4.04e-03 (max 8.66e-03, 271 / 326 tensors changed)
Reload bit-exact check	True

Optimizer state is not included (inference/eval only; the fp32 FSDP shards stay on HiPerGator /blue). Load with AutoModelForCausalLM.from_pretrained(..., torch_dtype=torch.bfloat16) or vLLM.

Use the bundled chat_template.jinja — it is NOT the stock SmolLM3 template. This checkpoint was behaviour-cloned with a task-specific template that (a) defaults to /no_think, (b) does not pre-fill an empty <think></think> block into the generation prompt, and (c) replaces the long default reasoning instructions with a compact format directive. The model is expected to emit <think>…</think><action>…</action> itself. Loading the stock template instead silently changes the prompt distribution.

Apache-2.0, same as the base model.

Downloads last month: 141

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for wayne377/SmolLM3-3B-SFT-WebShop

Base model

HuggingFaceTB/SmolLM3-3B-Base

Finetuned

HuggingFaceTB/SmolLM3-3B

Finetuned

(148)

this model