Instructions to use HuggingFaceTB/SmolLM-1.7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/SmolLM-1.7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceTB/SmolLM-1.7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM-1.7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM-1.7B-Instruct")
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 HuggingFaceTB/SmolLM-1.7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolLM-1.7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM-1.7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingFaceTB/SmolLM-1.7B-Instruct

SGLang

How to use HuggingFaceTB/SmolLM-1.7B-Instruct 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/SmolLM-1.7B-Instruct" \
    --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": "HuggingFaceTB/SmolLM-1.7B-Instruct",
		"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 "HuggingFaceTB/SmolLM-1.7B-Instruct" \
        --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": "HuggingFaceTB/SmolLM-1.7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingFaceTB/SmolLM-1.7B-Instruct with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/SmolLM-1.7B-Instruct
```

pls help: how to use model.onnx ?

by jennasu - opened Jul 19, 2024

Discussion

jennasu

Jul 19, 2024

•

edited Jul 19, 2024

#ENV:debian OS, python 3.7

#code
import onnxruntime as ort
import numpy as np
import onnx
model = onnx.load("/root/model_fp16.onnx")
ir_version = model.ir_version
print(f"Model IR version: {ir_version}")

#ERROR:
model = onnx.load("/root/model_fp16.onnx")
File "/usr/local/lib/python3.7/dist-packages/onnx/init.py", line 170, in load_model
model = load_model_from_string(s, format=format)
File "/usr/local/lib/python3.7/dist-packages/onnx/init.py", line 212, in load_model_from_string
return _deserialize(s, ModelProto())
File "/usr/local/lib/python3.7/dist-packages/onnx/init.py", line 143, in _deserialize
decoded = typing.cast(Optional[int], proto.ParseFromString(s))
google.protobuf.message.DecodeError: Error parsing message

eliebak

Aug 18, 2024

•

edited Aug 18, 2024

You can import onnx model in a similar way than with transformers:

from transformers import AutoTokenizer
from optimum.onnxruntime import ORTModelForCausalLM
import torch
import os

# Specify the local path to your cloned repository
# git clone https://huggingface.co/HuggingFaceTB/SmolLM-1.7B-Instruct
repo_path = "path/to/local/repo"

# cp repo_path/onnx/model.onnx repo_path/model.onnx -> moove the onnx model you want to the main folder

# Load the tokenizer and model from local paths
tokenizer = AutoTokenizer.from_pretrained(repo_path)
model = ORTModelForCausalLM.from_pretrained(repo_path)

# Prepare the input using the chat template
messages = [
    {"role": "system", "content": "You are a helpful AI assistant."},
    {"role": "user", "content": "What is the capital of France ?"}
]

# Apply the chat template
input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

# Generate the response
inputs = tokenizer(input_text, return_tensors="pt")
gen_tokens = model.generate(**inputs, do_sample=True, temperature=0.2, top_p=0.9, min_length=20, max_length=100)

# Decode and print the output
output = tokenizer.batch_decode(gen_tokens, skip_special_tokens=True)
print(output[0])

Ken-MY

Nov 11, 2024

This comment has been hidden

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