import torch
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "jjsprockel/Patologia_lora_model1",
    max_seq_length = 2048, # Choose any! Llama 3 is up to 8k
    dtype = None,
    load_in_4bit = True,
    )

FastLanguageModel.for_inference(model)

alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}

### Input:
{}

### Response:
{}"""

instruction = input("Ingresa la pregunta que tengas de Patología: ")

inputs = tokenizer(
[
    alpaca_prompt.format(
        instruction, # instruction
        "", # input
        "", # output - leave this blank for generation!
    )
], return_tensors = "pt").to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 2048)