Instructions to use HuggingFaceTB/SmolLM2-1.7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/SmolLM2-1.7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceTB/SmolLM2-1.7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-1.7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM2-1.7B-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]:]))

Transformers.js

How to use HuggingFaceTB/SmolLM2-1.7B-Instruct with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('text-generation', 'HuggingFaceTB/SmolLM2-1.7B-Instruct');

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceTB/SmolLM2-1.7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolLM2-1.7B-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/SmolLM2-1.7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingFaceTB/SmolLM2-1.7B-Instruct

SGLang

How to use HuggingFaceTB/SmolLM2-1.7B-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/SmolLM2-1.7B-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/SmolLM2-1.7B-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/SmolLM2-1.7B-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/SmolLM2-1.7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingFaceTB/SmolLM2-1.7B-Instruct with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/SmolLM2-1.7B-Instruct
```

GSM8K results replication

by sam-paech - opened Nov 3, 2024

Discussion

sam-paech

Nov 3, 2024

•

edited Nov 3, 2024

Hi!

I'm trying to replicate the gsm8k result, using lighteval:

lighteval accelerate \
    --model_args "pretrained=HuggingFaceTB/SmolLM2-1.7B-Instruct,max_gen_toks=800,max_length=2000,dtype=bfloat16" \
    --tasks "lighteval|gsm8k|5|1" \
    --override_batch_size 1 \
    --output_dir="./evals/"

It doesn't seem to be working for me. These are the results:

{
  "config_general": {
    "lighteval_sha": "?",
    "num_fewshot_seeds": 1,
    "override_batch_size": 1,
    "max_samples": null,
    "job_id": "",
    "start_time": 11280063.201784864,
    "end_time": 11281750.641923392,
    "total_evaluation_time_secondes": "1687.4401385281235",
    "model_name": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
    "model_sha": "7eb5a4069bde2ddf31c4303463d32e445d3e7d45",
    "model_dtype": "torch.bfloat16",
    "model_size": "3.19 GB"
  },
  "results": {
    "lighteval|gsm8k|5": {
      "maj@8": 0.001516300227445034,
      "maj@8_stderr": 0.0010717793485492638,
      "qem": 0.0,
      "qem_stderr": 0.0
    },
    "all": {
      "maj@8": 0.001516300227445034,
      "maj@8_stderr": 0.0010717793485492638,
      "qem": 0.0,
      "qem_stderr": 0.0
    }
  }

Any idea what I should be doing instead?

anton-l

Hugging Face Smol Models Research org Nov 19, 2024

Hello @sam-paech , the default pytorch batching in lighteval cuts off the generations at a single token for most batches if you set the model length to 2000 (due to some of the longer 5-shot prompts).
We're using VLLM's dynamic batching to overcome that: https://github.com/huggingface/smollm/blob/main/evaluation/README.md

sam-paech

Nov 20, 2024

Hello @sam-paech , the default pytorch batching in lighteval cuts off the generations at a single token for most batches if you set the model length to 2000 (due to some of the longer 5-shot prompts).
We're using VLLM's dynamic batching to overcome that: https://github.com/huggingface/smollm/blob/main/evaluation/README.md

Great thanks Anton, will try this.

loubnabnl changed discussion status to closed Nov 29, 2024

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