|
--- |
|
title: Gemma 2B Italian Sentiment Analysis Model |
|
tags: |
|
- sentiment-analysis |
|
- italian |
|
- autotrain |
|
- gemma-2b |
|
datasets: |
|
- custom |
|
library_name: transformers |
|
model: theoracle/11italian-sent |
|
license: other |
|
--- |
|
|
|
## Overview |
|
|
|
Introducing the `theoracle/11italian-sent` model, a highly specialized tool designed for sentiment analysis in Italian. Built on the Gemma 2B architecture and fine-tuned with a diverse set of Italian texts, this model can accurately classify sentences into positive, neutral, or negative sentiments. Whether analyzing customer feedback, social media posts, or news headlines, this model offers deep insights into the emotional tone of Italian texts. |
|
|
|
## Key Features |
|
|
|
- **Tailored for Italian Text**: Optimized to understand the nuances and complexities of the Italian language. |
|
- **Comprehensive Sentiment Analysis**: Categorizes text into positive, neutral, or negative sentiments with high accuracy. |
|
- **Powered by Gemma 2B and AutoTrain**: Utilizes the Gemma 2B architecture for advanced text processing and is trained using Hugging Face's AutoTrain for maximum efficiency. |
|
|
|
## Usage |
|
|
|
Here's how to utilize this model for sentiment analysis on Italian text: |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model_path = "theoracle/11italian-sent" |
|
tokenizer = AutoTokenizer.from_pretrained(model_path) |
|
model = AutoModelForCausalLM.from_pretrained( |
|
model_path, |
|
device_map="auto", |
|
torch_dtype='auto' |
|
).eval() |
|
|
|
# Prepare your hotel review or any Italian text |
|
prompt = ''' |
|
Analyze the sentiment of the hotel review enclosed in square brackets, determine if it is positive, neutral, or negative, and return the answer as the corresponding sentiment label "positive" or "neutral" or "negative" [Inserisci qui la tua recensione dell'hotel] |
|
''' |
|
|
|
# Tokenize and generate the response |
|
encoding = tokenizer(prompt, return_tensors='pt', padding=True, truncation=True, max_length=500, add_special_tokens=True) |
|
input_ids = encoding['input_ids'] |
|
attention_mask = encoding['attention_mask'] |
|
|
|
output_ids = model.generate( |
|
input_ids.to('cuda'), |
|
attention_mask=attention_mask.to('cuda'), |
|
max_new_tokens=300, |
|
pad_token_id=tokenizer.eos_token_id |
|
) |
|
|
|
response = tokenizer.decode(output_ids[0], skip_special_tokens=True) |
|
print(response) |
|
``` |
|
|
|
## Application Scenarios |
|
|
|
This model is invaluable for: |
|
- Businesses analyzing customer reviews in Italian. |
|
- Social media monitoring for sentiment analysis. |
|
- Researchers studying public opinion on various topics through Italian text. |
|
|
|
## Training and Technology |
|
|
|
`theoracle/11italian-sent` is trained with AutoTrain, ensuring optimal training efficiency, and is built on the Gemma 2B architecture, known for its high performance in text generation and understanding tasks. The combination offers unparalleled accuracy and speed in processing Italian texts for sentiment analysis. |
|
|
|
## License |
|
|
|
This model is available under an "other" license, suitable for both commercial and non-commercial use, though users are encouraged to review the license details for full compliance with their intended applications. |
