Instructions to use fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym with Transformers:

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

pipe = pipeline("text-generation", model="fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym")
model = AutoModelForCausalLM.from_pretrained("fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym")
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 fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym with Transformers.js:

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

// Allocate pipeline
const pipe = await pipeline('text-generation', 'fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym');

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym

SGLang

How to use fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym 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 "fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym" \
    --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": "fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym",
		"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 "fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym" \
        --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": "fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym with Docker Model Runner:
```
docker model run hf.co/fbaldassarri/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym
```

HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym / README.md

fbaldassarri

Update README.md

a296606 verified over 1 year ago

preview code

raw

history blame contribute delete

2.23 kB

	---
	language:
	- en
	license: apache-2.0
	library_name: transformers
	tags:
	- autoround
	- auto-round
	- intel
	- gptq
	- auto-gptq
	- autogptq
	- woq
	- pytorch
	- transformers
	- safetensors
	- onnx
	- transformers.js
	model_name: SmolLM2 1.7B Instruct
	base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
	inference: false
	model_creator: HuggingFaceTB
	pipeline_tag: text-generation
	prompt_template: '{prompt}
	'
	quantized_by: fbaldassarri
	---

	## Model Information

	Quantized version of [HuggingFaceTB/SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct) using torch.float32 for quantization tuning.
	- 4 bits (INT4)
	- group size = 128
	- Asymmetrical Quantization
	- Method AutoGPTQ

	Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round)

	Note: this INT4 version of SmolLM2-1.7B-Instruct has been quantized to run inference through CPU.

	## Replication Recipe

	### Step 1 Install Requirements

	I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment.

	```
	python -m pip install <package> --upgrade
	```

	- accelerate==1.0.1
	- auto_gptq==0.7.1
	- neural_compressor==3.1
	- torch==2.3.0+cpu
	- torchaudio==2.5.0+cpu
	- torchvision==0.18.0+cpu
	- transformers==4.45.2

	### Step 2 Build Intel Autoround wheel from sources

	```
	python -m pip install git+https://github.com/intel/auto-round.git
	```

	### Step 3 Script for Quantization

	```
	from transformers import AutoModelForCausalLM, AutoTokenizer
	model_name = "HuggingFaceTB/SmolLM2-1.7B-Instruct"
	model = AutoModelForCausalLM.from_pretrained(model_name)
	tokenizer = AutoTokenizer.from_pretrained(model_name)
	from auto_round import AutoRound
	bits, group_size, sym = 4, 128, False
	autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym)
	autoround.quantize()
	output_dir = "./AutoRound/HuggingFaceTB_SmolLM2-1.7B-Instruct-auto_gptq-int4-gs128-asym"
	autoround.save_quantized(output_dir, format='auto_gptq', inplace=True)
	```

	## License

	[Apache 2.0 License](https://choosealicense.com/licenses/apache-2.0/)

	## Disclaimer

	This quantized model comes with no warrenty. It has been developed only for research purposes.