metadata
license: mit
language:
- it
This model is a fine-tuned version of bart-it on a lfqa dataset (pubmed_qa, webgpt_comparisons, sapere.it, stackexchange_titlebody_best_voted_answer_jsonl, lfqa_preprocessed - partially translated)
Usage
import torch
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
model_name = "efederici/bart-lfqa-it"
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
model = model.to(device)
query = "<string>"
documents = [
"<string>",
"<string>",
...
]
docs = "<p> " + " <p> ".join([d for d in documents])
q = "Q: {}\n\nC: {}".format(query, docs)
input_qc = tokenizer(query_and_docs, truncation=True, padding=True, return_tensors="pt")
generated_answers_encoded = model.generate(
input_ids=input_qc["input_ids"].to(device),
attention_mask=input_qc["attention_mask"].to(device),
min_length=64,
max_length=256,
do_sample=False,
early_stopping=True,
num_beams=8,
temperature=1.0,
top_k=None,
top_p=None,
eos_token_id=tokenizer.eos_token_id,
no_repeat_ngram_size=3,
num_return_sequences=1
)
output = tokenizer.batch_decode(generated_answers_encoded, skip_special_tokens=True,clean_up_tokenization_spaces=True)[0]
print(output)