update app

app.py

@@ -20,6 +20,15 @@ import gradio as gr
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
 from threading import Thread
+import subprocess
+
+
+try:
+    __import__("flash_attn")
+    print(f'El paquete ya está instalado.')
+except ModuleNotFoundError:
+    subprocess.check_call(["python", '-m', 'pip', 'install', 'flash_attn'])
+    print(f'El paquete ha sido instalado.')
 
 #tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
 #model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1", torch_dtype=torch.float16)

requirements.txt

@@ -1,4 +1,3 @@
-flash_attn
 torch==2.0.1
 deepspeed
 sentencepiece