Update app.py
Browse files
app.py
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
import pandas as pd
|
2 |
import streamlit as st
|
3 |
from transformers import pipeline
|
|
|
4 |
from carga_articulos import cargar_articulos
|
5 |
from preprocesamiento_articulos import limpieza_articulos
|
6 |
from entrenamiento_modelo import term_document_matrix, tf_idf_score
|
@@ -16,14 +17,9 @@ def crear_indice():
|
|
16 |
td_idf_matrix.to_csv('articulos_indexados.csv')
|
17 |
|
18 |
def load_qa_model():
|
19 |
-
|
20 |
-
'
|
21 |
-
model=
|
22 |
-
tokenizer=(
|
23 |
-
'mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es',
|
24 |
-
{"use_fast": False} # Este modelo aun no es compatible con fast tokenizer
|
25 |
-
)
|
26 |
-
)
|
27 |
return model
|
28 |
|
29 |
# 4. Use streamlit to create a web app
|
|
|
1 |
import pandas as pd
|
2 |
import streamlit as st
|
3 |
from transformers import pipeline
|
4 |
+
from transformers import AutoTokenizer, DistilBertForQuestionAnswering
|
5 |
from carga_articulos import cargar_articulos
|
6 |
from preprocesamiento_articulos import limpieza_articulos
|
7 |
from entrenamiento_modelo import term_document_matrix, tf_idf_score
|
|
|
17 |
td_idf_matrix.to_csv('articulos_indexados.csv')
|
18 |
|
19 |
def load_qa_model():
|
20 |
+
|
21 |
+
tokenizer = AutoTokenizer.from_pretrained('mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es', use_fast="false")
|
22 |
+
model = DistilBertForQuestionAnswering.from_pretrained("mrm8488/distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es", device_map="auto", trust_remote_code=True, torch_dtype=torch.bfloat16)
|
|
|
|
|
|
|
|
|
|
|
23 |
return model
|
24 |
|
25 |
# 4. Use streamlit to create a web app
|