Load the tokenizer, model, and data collator
MODEL_NAME = "google/flan-t5-base" device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
if device.type == 'cuda': tokenizer = T5Tokenizer.from_pretrained(MODEL_NAME) model = T5ForConditionalGeneration.from_pretrained(MODEL_NAME, device_map="auto")
elif device.type == 'cpu': tokenizer = T5Tokenizer.from_pretrained(MODEL_NAME) model = T5ForConditionalGeneration.from_pretrained(MODEL_NAME)
#data_collator = DataCollatorForSeq2Seq(tokenizer=tokenizer, model=model)
data_collator = DataCollatorWithPadding(tokenizer=tokenizer) # do padding automatic according size of input_str
Definir configuracao LORA
lora_config = LoraConfig( task_type = TaskType.SEQ_2_SEQ_LM, r = 16, lora_alpha = 32, lora_dropout = 0.1, target_modules = ["q", "v"] )
model = get_peft_model(model, lora_config)
F1-score%
Domain
Laptop 78.285714
Restaurant 77.762846
book 54.166667
beauty 51.600000
toy 51.600000
pet 46.000000
grocery 44.000000
fashion 43.700000
home 41.583333
electronics 41.176471
AVALIAR PARA CONFIRMAR