Spaces:
Runtime error
Runtime error
File size: 1,008 Bytes
18475e7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 |
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import os
# Obtener el token de acceso desde las variables de entorno
hf_token = os.getenv("HF_TOKEN")
model_name = "epfl-llm/meditron-7b"
tokenizer = AutoTokenizer.from_pretrained(model_name, token=hf_token)
model = AutoModelForCausalLM.from_pretrained(model_name, token=hf_token)
# Función para generar respuesta del modelo
def generate_response(prompt):
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(inputs.input_ids, max_length=200, pad_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
return response
# Configurar la interfaz de Gradio
def chat(paciente_input):
prompt = f"Paciente: {paciente_input}\nDoctor:"
response = generate_response(prompt)
return response
iface = gr.Interface(fn=chat, inputs="text", outputs="text", title="Consulta Médica con Meditron-7B")
iface.launch()
|