Instructions to use basilepp19/bloom-1b7-evalita with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use basilepp19/bloom-1b7-evalita with Transformers:

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

pipe = pipeline("text-generation", model="basilepp19/bloom-1b7-evalita")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("basilepp19/bloom-1b7-evalita")
model = AutoModelForCausalLM.from_pretrained("basilepp19/bloom-1b7-evalita")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use basilepp19/bloom-1b7-evalita with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "basilepp19/bloom-1b7-evalita"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "basilepp19/bloom-1b7-evalita",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/basilepp19/bloom-1b7-evalita

SGLang

How to use basilepp19/bloom-1b7-evalita 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 "basilepp19/bloom-1b7-evalita" \
    --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": "basilepp19/bloom-1b7-evalita",
		"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 "basilepp19/bloom-1b7-evalita" \
        --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": "basilepp19/bloom-1b7-evalita",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use basilepp19/bloom-1b7-evalita with Docker Model Runner:
```
docker model run hf.co/basilepp19/bloom-1b7-evalita
```

Model Card for Model ID

This model is obtained by fine-tuning the BLOOM model over two Italian classification task prompts without language adaptation. To deal with this step, we decided to use data from two well-known EVALITA tasks: AMI2020 (misogyny detection) and HASPEEDE-v2-2020 (hate-speech detection).

Model Details

Model Description

The BLOOM model is directly fine-tuned over two Italian classification task prompts using two well-known EVALITA tasks: AMI2020 (misogyny detection) and HASPEEDE-v2-2020 (hate-speech detection).

We transformed the training data of the two tasks into an LLM prompt following a template. For the AMI task, we used the following template:

instruction: Nel testo seguente si esprime odio contro le donne? Rispondi sì o no., input: <text>, output: <sì/no>.

Similarly, for HASPEEDE we used:

instruction: “Il testo seguente incita all’odio? Rispondi sì o no., input: <text>, output: <sì/no>.

To fill these templates, we mapped the label "1" with the word "sì" and the label "0" with the word "no", <text> is just the sentence from the dataset to classify.

To fine-tune the model, we use the script available here: https://github.com/hyintell/BLOOM-fine-tuning/tree/main

Developed by: Pierpaolo Basile, Pierluigi Cassotti, Marco Polignano, Lucia Siciliani, Giovanni Semeraro. Department of Computer Science, University of Bari Aldo Moro, Italy
Model type: BLOOM
Language(s) (NLP): Italian
License: BigScience BLOOM RAIL 1.0

Citation

Pierpaolo Basile, Pierluigi Cassotti, Marco Polignano, Lucia Siciliani, Giovanni Semeraro. On the impact of Language Adaptation for Large Language Models: A case study for the Italian language using only open resources. Proceedings of the Ninth Italian Conference on Computational Linguistics (CLiC-it 2023).

Downloads last month: 4