Update app.py

app.py

@@ -22,9 +22,17 @@ inputs = tokenizer(prompt, return_tensors="pt")
 outputs = model(**inputs) #, labels=inputs["input_ids"])
 
 
-last_hidden_states = outputs.last_hidden_state
+# last_hidden_states = outputs.last_hidden_state
+
+# output = last_hidden_states #['last_hidden_states']
+
+
+# input_text = "The theory of special relativity states "
+# input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
+
+outputs = model.generate(**inputs)
+output = tokenizer.batch_decode(outputs, skip_special_tokens=True)
 
-output = last_hidden_states #['last_hidden_states']
 
 # decoded = tokenizer.decode(output)
 
@@ -43,8 +51,8 @@ output = last_hidden_states #['last_hidden_states']
 with st.container():
     st.write('\n\n')
     st.write('LLM-LANAChat\n\n')
+    st.write(outputs)
     st.write(output)
-    st.write(type(output))
 
 print('\nsaida gerada.')
 print('\n\n')