<start_of_turn>user\n
Analyze the question, the expected answer, and the student's response. Determine if the student's answer is conceptually correct in relation to the expected answer, regardless of the exact wording. An answer will be considered correct if it accurately identifies the key information requested in the question, even if expressed differently. Return True if the student's answer is correct or False otherwise. Add a brief comment explaining the rationale behind the answer being correct or incorrect.

Question: {question}
Expected Answer: {best_answer}
Student Answer: {student_answer}<end_of_turn>\n
<start_of_turn>model"

!pip install -q -U bitsandbytes
!pip install -q -U git+https://github.com/huggingface/transformers.git
!pip install -q -U git+https://github.com/huggingface/peft.git
!pip install -q -U git+https://github.com/huggingface/accelerate.git
!pip install -q -U gradio

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, GemmaTokenizer
from peft import AutoPeftModelForCausalLM
import torch
import re

# Carga el modelo y el tokenizer
model_id = "google/gemma-7b-it"
adapter = "nmarafo/Gemma-7B-it-4bit-TrueFalse-Feedback"

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoPeftModelForCausalLM.from_pretrained(adapter, quantization_config=bnb_config, device_map={"":0})

def predict(question, best_answer, student_answer, language):
    if language == "English":
        system_message = "Analyze the question, the expected answer, and the student's response. Determine if the student's answer is conceptually correct in relation to the expected answer, regardless of the exact wording. Return True if the student's answer is correct or False otherwise. Add a brief comment explaining the rationale behind the answer being correct or incorrect."
    else:  # Asumimos que cualquier otra opción será Español
        system_message = "Analiza la pregunta, la respuesta esperada y la respuesta del estudiante. Determina si la respuesta del estudiante es conceptualmente correcta en relación con la respuesta esperada, independientemente de la redacción exacta. Devuelve Verdadero si la respuesta del estudiante es correcta o Falso en caso contrario. Añade un breve comentario explicando el razonamiento detrás de la corrección o incorrección de la respuesta."

    prompt = f"{system_message}\n\nQuestion: {question}\nExpected Answer: {best_answer}\nStudent Answer: {student_answer}"
    prompt_template=f"<bos><start_of_turn>user\n{prompt}<end_of_turn>\n<start_of_turn>model"

    # Ajusta aquí para incluir attention_mask
    encoding = tokenizer(prompt_template, return_tensors='pt', padding=True, truncation=True, max_length=256)
    input_ids = encoding['input_ids'].cuda()
    attention_mask = encoding['attention_mask'].cuda()

    output = model.generate(input_ids, attention_mask=attention_mask,
                            temperature=0.5, do_sample=True, top_p=0.49,
                            top_k=40, max_new_tokens=256, pad_token_id=tokenizer.eos_token_id)
    response = tokenizer.decode(output[0], skip_special_tokens=True)

    return response

import gradio as gr

iface = gr.Interface(
    fn=predict,
    inputs=[
        gr.Textbox(lines=2, placeholder="Pregunta"),
        gr.Textbox(lines=2, placeholder="Mejor Respuesta"),
        gr.Textbox(lines=2, placeholder="Respuesta del Estudiante"),
        gr.Radio(choices=["English", "Español"], label="Idioma")
    ],
    outputs=gr.Textbox(label="Respuesta del Modelo")
)
iface.launch(share=True,debug=True)