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

Libraries

How to use belyakoff/SmolLM2-360M-Instruct-FT with Transformers:

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

pipe = pipeline("text-generation", model="belyakoff/SmolLM2-360M-Instruct-FT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("belyakoff/SmolLM2-360M-Instruct-FT")
model = AutoModelForCausalLM.from_pretrained("belyakoff/SmolLM2-360M-Instruct-FT")
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

vLLM

How to use belyakoff/SmolLM2-360M-Instruct-FT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "belyakoff/SmolLM2-360M-Instruct-FT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "belyakoff/SmolLM2-360M-Instruct-FT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/belyakoff/SmolLM2-360M-Instruct-FT

SGLang

How to use belyakoff/SmolLM2-360M-Instruct-FT 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 "belyakoff/SmolLM2-360M-Instruct-FT" \
    --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": "belyakoff/SmolLM2-360M-Instruct-FT",
		"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 "belyakoff/SmolLM2-360M-Instruct-FT" \
        --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": "belyakoff/SmolLM2-360M-Instruct-FT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use belyakoff/SmolLM2-360M-Instruct-FT with Docker Model Runner:
```
docker model run hf.co/belyakoff/SmolLM2-360M-Instruct-FT
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Versions

v1: SFT -- 7658aab7702e56d9f5fa3b33bf7adcdae92f536b

Example

from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "belyakoff/SmolLM2-360M-Instruct-FT"

device = "cuda" # for GPU usage or "cpu" for CPU usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
# for multiple GPUs install accelerate and do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")`
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)

messages = [{"role": "user", "content": "Столица России?"}]
input_text=tokenizer.apply_chat_template(messages, tokenize=False)
print(input_text)
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)
print(tokenizer.decode(outputs[0]))
# Столица России — Москва. Это один из самых известных и культурно значимых городов в мире.

Limitations

Don't change system prompt. Changing system prompt will make the model go crazy.

Downloads last month: 8

Safetensors

Model size

0.4B params

Tensor type

F32

Model tree for belyakoff/SmolLM2-360M-Instruct-FT

Base model

HuggingFaceTB/SmolLM2-360M

Quantized

HuggingFaceTB/SmolLM2-360M-Instruct

Finetuned

(144)

this model

Quantizations

3 models

belyakoff
/

SmolLM2-360M-Instruct-FT

Versions

Example

Limitations

Model tree for belyakoff/SmolLM2-360M-Instruct-FT

Dataset used to train belyakoff/SmolLM2-360M-Instruct-FT