Instructions to use morenolq/BART-IT-LSG-4096 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use morenolq/BART-IT-LSG-4096 with Transformers:

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

pipe = pipeline("text-generation", model="morenolq/BART-IT-LSG-4096", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("morenolq/BART-IT-LSG-4096", trust_remote_code=True)
model = AutoModelForSeq2SeqLM.from_pretrained("morenolq/BART-IT-LSG-4096", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use morenolq/BART-IT-LSG-4096 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "morenolq/BART-IT-LSG-4096"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "morenolq/BART-IT-LSG-4096",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/morenolq/BART-IT-LSG-4096

SGLang

How to use morenolq/BART-IT-LSG-4096 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 "morenolq/BART-IT-LSG-4096" \
    --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": "morenolq/BART-IT-LSG-4096",
		"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 "morenolq/BART-IT-LSG-4096" \
        --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": "morenolq/BART-IT-LSG-4096",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use morenolq/BART-IT-LSG-4096 with Docker Model Runner:
```
docker model run hf.co/morenolq/BART-IT-LSG-4096
```

morenolq commited on Feb 26, 2025

Commit

5886f20

verified ·

1 Parent(s): 96332cc

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -4,8 +4,6 @@ language:
 tags:
 - text2text-generation
 - summarization
-- legal-ai
-- italian-law
 license: mit
 datasets:
 - joelniklaus/Multi_Legal_Pile
@@ -28,6 +26,8 @@ They build upon **BART-IT** ([`morenolq/bart-it`](https://huggingface.co/morenol
   - **Trained on legal documents** such as **statutes, case law, and contracts** 📑
   - **Not fine-tuned for specific tasks** (requires further adaptation)
 ## 📂 Available Models
 | Model | Description | Link |
@@ -38,8 +38,8 @@ They build upon **BART-IT** ([`morenolq/bart-it`](https://huggingface.co/morenol
 | **LEGIT-SCRATCH-BART** | Trained from scratch on **Italian legal texts** | [🔗 Link](https://huggingface.co/morenolq/LEGIT-SCRATCH-BART) |
 | **LEGIT-SCRATCH-BART-LSG-4096** | Trained from scratch with **LSG attention**, supporting **4,096 tokens** | [🔗 Link](https://huggingface.co/morenolq/LEGIT-SCRATCH-BART-LSG-4096) |
 | **LEGIT-SCRATCH-BART-LSG-16384** | Trained from scratch with **LSG attention**, supporting **16,384 tokens** | [🔗 Link](https://huggingface.co/morenolq/LEGIT-SCRATCH-BART-LSG-16384) |
-| **BART-IT-LSG-4096** | `morenolq/bart-it` with **LSG attention**, supporting **4,096 tokens** (no legal adaptation) | [🔗 Link](https://huggingface.co/morenolq/BART-IT-LSG-4096)
-| **BART-IT-LSG-16384** | `morenolq/bart-it` with **LSG attention**, supporting **16,384 tokens** (no legal adaptation) | [🔗 Link](https://huggingface.co/morenolq/BART-IT-LSG-16384) |
 ---
@@ -74,10 +74,10 @@ model = BartForConditionalGeneration.from_pretrained(model_name)
 input_text = "<mask> 1234: Il contratto si intende concluso quando..."
 inputs = tokenizer(input_text, return_tensors="pt", max_length=4096, truncation=True)
-# Pre-trained model fill the mask
-output_ids = model.generate(inputs.input_ids, max_length=150, num_beams=4, early_stopping=True)
-output_text = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
-print("📝:", output_text)
 ```
 ---

 tags:
 - text2text-generation
 - summarization
 license: mit
 datasets:
 - joelniklaus/Multi_Legal_Pile
   - **Trained on legal documents** such as **statutes, case law, and contracts** 📑
   - **Not fine-tuned for specific tasks** (requires further adaptation)
+⚠️ This specific model is pre-trained on general-purpose Italian text! Please select the best model from the table below.
 ## 📂 Available Models
 | Model | Description | Link |
 | **LEGIT-SCRATCH-BART** | Trained from scratch on **Italian legal texts** | [🔗 Link](https://huggingface.co/morenolq/LEGIT-SCRATCH-BART) |
 | **LEGIT-SCRATCH-BART-LSG-4096** | Trained from scratch with **LSG attention**, supporting **4,096 tokens** | [🔗 Link](https://huggingface.co/morenolq/LEGIT-SCRATCH-BART-LSG-4096) |
 | **LEGIT-SCRATCH-BART-LSG-16384** | Trained from scratch with **LSG attention**, supporting **16,384 tokens** | [🔗 Link](https://huggingface.co/morenolq/LEGIT-SCRATCH-BART-LSG-16384) |
+| **BART-IT-LSG-4096** | `morenolq/bart-it` with **LSG attention**, supporting **4,096 tokens** (⚠️ no legal adaptation) | [🔗 Link](https://huggingface.co/morenolq/BART-IT-LSG-4096)
+| **BART-IT-LSG-16384** | `morenolq/bart-it` with **LSG attention**, supporting **16,384 tokens** (⚠️ no legal adaptation) | [🔗 Link](https://huggingface.co/morenolq/BART-IT-LSG-16384) |
 ---
 input_text = "<mask> 1234: Il contratto si intende concluso quando..."
 inputs = tokenizer(input_text, return_tensors="pt", max_length=4096, truncation=True)
+# Generate summary
+summary_ids = model.generate(inputs.input_ids, max_length=150, num_beams=4, early_stopping=True)
+summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+print("📝 Summary:", summary)
 ```
 ---