Instructions to use VerbACxSS/sempl-it-gpt2-small-italian with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VerbACxSS/sempl-it-gpt2-small-italian with Transformers:

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

pipe = pipeline("text-generation", model="VerbACxSS/sempl-it-gpt2-small-italian")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VerbACxSS/sempl-it-gpt2-small-italian")
model = AutoModelForCausalLM.from_pretrained("VerbACxSS/sempl-it-gpt2-small-italian", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use VerbACxSS/sempl-it-gpt2-small-italian with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VerbACxSS/sempl-it-gpt2-small-italian"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VerbACxSS/sempl-it-gpt2-small-italian",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/VerbACxSS/sempl-it-gpt2-small-italian

SGLang

How to use VerbACxSS/sempl-it-gpt2-small-italian 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 "VerbACxSS/sempl-it-gpt2-small-italian" \
    --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": "VerbACxSS/sempl-it-gpt2-small-italian",
		"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 "VerbACxSS/sempl-it-gpt2-small-italian" \
        --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": "VerbACxSS/sempl-it-gpt2-small-italian",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use VerbACxSS/sempl-it-gpt2-small-italian with Docker Model Runner:
```
docker model run hf.co/VerbACxSS/sempl-it-gpt2-small-italian
```

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VerbACxSS/sempl-it-gpt2-small-italian", model_max_length=1024)
model = AutoModelForCausalLM.from_pretrained("VerbACxSS/sempl-it-gpt2-small-italian")

model.eval()

text_to_simplify = 'Nella fattispecie, questo documento è di natura prescrittiva'
prompt = f'### [Input]:\n{text_to_simplify}\n\n###[Output]:\n'

x = tokenizer(prompt, max_length=1024, truncation=True, padding=True, return_tensors='pt').input_ids
y = model.generate(x, max_length=1024)[0]
y_dec = tokenizer.decode(y, max_length=1024, truncation=True)
output = y_dec.split('###[Output]:\n')[1].split('<|endoftext|>')[0].strip()

print(output)

Acknowledgements

This contribution is a result of the research conducted within the framework of the PRIN 2020 (Progetti di Rilevante Interesse Nazionale) "VerbACxSS: on analytic verbs, complexity, synthetic verbs, and simplification. For accessibility" (Prot. 2020BJKB9M), funded by the Italian Ministero dell'Università e della Ricerca.

Downloads last month: 146

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for VerbACxSS/sempl-it-gpt2-small-italian

Base model

GroNLP/gpt2-small-italian

Finetuned

(2)

this model

Collection including VerbACxSS/sempl-it-gpt2-small-italian

sempl-it-v1

Collection

3 items • Updated Apr 3, 2025