Update README.md

README.md

@@ -55,7 +55,7 @@ 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, temperature, top_p, top_k):
+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
@@ -64,18 +64,17 @@ def predict(question, best_answer, student_answer, language, temperature, top_p,
     prompt = f"{system_message}\n\nQuestion: {question}\nExpected Answer: {best_answer}\nStudent Answer: {student_answer}"
     prompt_template=f"<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=temperature, do_sample=True, top_p=top_p,
-                            top_k=top_k, max_new_tokens=256, pad_token_id=tokenizer.eos_token_id)
+                            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)
-    pattern = r"\[INST\].*?\[\/INST\]\s*(True|False)"
-    cleaned_response = re.sub(pattern, r"\1", response, flags=re.DOTALL)
 
-    return
+    return response
 
 import gradio as gr
 
@@ -85,14 +84,11 @@ iface = gr.Interface(
         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"),
-        gr.Slider(minimum=0.1, maximum=1.0, step=0.1, value=0.5, label="Temperature"),
-        gr.Slider(minimum=0.1, maximum=1.0, step=0.01, value=0.49, label="Top P"),
-        gr.Slider(minimum=0, maximum=100, step=1, value=40, label="Top K")
+        gr.Radio(choices=["English", "Español"], label="Idioma")
     ],
     outputs=gr.Textbox(label="Respuesta del Modelo")
 )
-iface.launch(share=True,debug=True)    
+iface.launch(share=True,debug=True)   
 
 ```