Instructions to use HuggingFaceTB/SmolLM2-360M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/SmolLM2-360M with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceTB/SmolLM2-360M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-360M")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM2-360M")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceTB/SmolLM2-360M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolLM2-360M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM2-360M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceTB/SmolLM2-360M

SGLang

How to use HuggingFaceTB/SmolLM2-360M 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 "HuggingFaceTB/SmolLM2-360M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM2-360M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "HuggingFaceTB/SmolLM2-360M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM2-360M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceTB/SmolLM2-360M with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/SmolLM2-360M
```

Sample Model Script for bfloat16 downloads safetensors parameters files then declares mismatch in their dimensions.

by MartialTerran - opened Dec 2, 2024

Discussion

MartialTerran

Dec 2, 2024

I copy-pasted the python script on this webpage for the bfloat16 model and removed device_map="auto" from model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto", torch_dtype=torch.bfloat16)
Then the script downloaded safetensors:

C:\Users\User\OneDrive\Desktop\SmolLM2>python bfloat16_SmolLM2_360_model.py
Downloading model.safetensors: 100%|████████████████████████████████████████████████| 724M/724M [01:02<00:00, 11.6MB/s]
C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\huggingface_hub\file_download.py:133: UserWarning: huggingface_hub cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\Users\User.cache\huggingface\hub. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the HF_HUB_DISABLE_SYMLINKS_WARNING environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.
To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development
warnings.warn(message)

Next, the script reported size mismatches:

A module that was compiled using NumPy 1.x cannot be run in
NumPy 2.1.3 as it may crash. To support both 1.x and 2.x
versions of NumPy, modules must be compiled with NumPy 2.0.
Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.

If you are a user of the module, the easiest solution will be to
downgrade to 'numpy<2' or try to upgrade the affected module.
We expect that some modules will need time to support NumPy 2.

Traceback (most recent call last): File "C:\Users\User\OneDrive\Desktop\SmolLM2\bfloat16_SmolLM2_360_model.py", line 12, in
model = AutoModelForCausalLM.from_pretrained(checkpoint, torch_dtype=torch.bfloat16)
File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\transformers\models\auto\auto_factory.py", line 484, in from_pretrained
return model_class.from_pretrained(
File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\transformers\modeling_utils.py", line 2604, in from_pretrained
state_dict = load_state_dict(resolved_archive_file)
File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\transformers\modeling_utils.py", line 461, in load_state_dict
return safe_load_file(checkpoint_file)
File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\safetensors\torch.py", line 261, in load_file
result[k] = f.get_tensor(k)
File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\storage.py", line 234, in getitem
return super().getitem(*args, **kwargs)
C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\storage.py:234: UserWarning: Failed to initialize NumPy: _ARRAY_API not found (Triggered internally at ..\torch\csrc\utils\tensor_numpy.cpp:84.)
return super().getitem(*args, **kwargs)
Traceback (most recent call last):
File "C:\Users\User\OneDrive\Desktop\SmolLM2\bfloat16_SmolLM2_360_model.py", line 12, in
model = AutoModelForCausalLM.from_pretrained(checkpoint, torch_dtype=torch.bfloat16)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\transformers\models\auto\auto_factory.py", line 484, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\transformers\modeling_utils.py", line 2881, in from_pretrained
) = cls._load_pretrained_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\User\AppData\Local\Programs\Python\Python311\Lib\site-packages\transformers\modeling_utils.py", line 3278, in _load_pretrained_model
raise RuntimeError(f"Error(s) in loading state_dict for {model.class.name}:\n\t{error_msg}")
RuntimeError: Error(s) in loading state_dict for LlamaForCausalLM:
size mismatch for model.layers.0.self_attn.k_proj.weight: copying a param with shape torch.Size([320, 960]) from checkpoint, the shape in current model is torch.Size([960, 960]).
size mismatch for model.layers.0.self_attn.v_proj.weight: copying a param with shape torch.Size([320, 960]) from checkpoint, the shape in current model is torch.Size([960, 960]).
size mismatch for model.layers.1.self_attn.k_proj.weight: copying a param with shape torch.Size([320, 960]) from checkpoint, the shape in current model is torch.Size([960, 960]).
size mismatch for model.layers.1.self_a
[[ etcetera]]
size mismatch for model.layers.31.self_attn.k_proj.weight: copying a param with shape torch.Size([320, 960]) from checkpoint, the shape in current model is torch.Size([960, 960]).
size mismatch for model.layers.31.self_attn.v_proj.weight: copying a param with shape torch.Size([320, 960]) from checkpoint, the shape in current model is torch.Size([960, 960]).
You may consider adding ignore_mismatched_sizes=True in the model from_pretrained method.

C:\Users\User\OneDrive\Desktop\SmolLM2>

MartialTerran

Dec 2, 2024

This is the script that I ran:

pip install accelerate

Using torch.bfloat16

import torch

from transformers import AutoTokenizer, AutoModelForCausalLM
checkpoint = "HuggingFaceTB/SmolLM2-360M"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)

for fp16 use `torch_dtype=torch.float16` instead

#model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto", torch_dtype=torch.bfloat16)
model = AutoModelForCausalLM.from_pretrained(checkpoint, torch_dtype=torch.bfloat16)
inputs = tokenizer.encode("Gravity is", return_tensors="pt").to("cuda")
outputs = model.generate(inputs)

print(tokenizer.decode(outputs[0]))
print(f"Memory footprint: {model.get_memory_footprint() / 1e6:.2f} MB")

Memory footprint: 723.56 MB

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Sample Model Script for bfloat16 downloads safetensors parameters files then declares mismatch in their dimensions.

pip install accelerate

Using torch.bfloat16

for fp16 use torch_dtype=torch.float16 instead

Memory footprint: 723.56 MB

for fp16 use `torch_dtype=torch.float16` instead