Update app.py

app.py

@@ -1,18 +1,19 @@
 import gradio as gr
-from langchain.llms import HuggingFacePipeline
-from transformers import AutoTokenizer
+from langchain.llms import HuggingFacePipeline, CTransformers
+from transformers import AutoTokenizer, AutoModel
 import transformers
 import torch
 import warnings
 warnings.filterwarnings('ignore')
 
-# llm = CTransformers(model="TheBloke/Llama-2-7B-Chat-GGML", model_file="llama-2-7b-chat.ggmlv3.q3_K_S.bin")
+model = CTransformers(model="TheBloke/Llama-2-7B-Chat-GGML", model_file="llama-2-7b-chat.ggmlv3.q3_K_S.bin")
+
 
 tokenizer=AutoTokenizer.from_pretrained(model="TheBloke/Llama-2-7B-Chat-GGML", model_file="llama-2-7b-chat.ggmlv3.q3_K_S.bin")
 
 pipeline=transformers.pipeline(
     "text-generation",
-    model=(model="TheBloke/Llama-2-7B-Chat-GGML", model_file="llama-2-7b-chat.ggmlv3.q3_K_S.bin"),
+    model=model,
     tokenizer=tokenizer,
     torch_dtype=torch.bfloat16,
     trust_remote_code=True,