Update app.py

app.py

@@ -6,14 +6,14 @@ from langchain import LLMChain, HuggingFacePipeline, PromptTemplate
 import os
 from ctransformers import AutoModelForCausalLM, AutoTokenizer
 
-model = AutoModelForCausalLM.from_pretrained("marella/gpt-2-ggml", hf=True)
-tokenizer = AutoTokenizer.from_pretrained(model)
+# model = AutoModelForCausalLM.from_pretrained("marella/gpt-2-ggml", hf=True)
+# tokenizer = AutoTokenizer.from_pretrained(model)
 
 access_token = os.getenv("Llama2")
 
 def greet(text):
 
-    model = AutoModelForCausalLM.from_pretrained("marella/gpt-2-ggml", hf=True)
+    model = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGML", model_file = 'llama-2-7b-chat.ggmlv3.q4_K_S.bin', hf=True)
     tokenizer = AutoTokenizer.from_pretrained(model)
     
     # model = "meta-llama/Llama-2-7b-hf"
@@ -35,7 +35,7 @@ def greet(text):
     # token=access_token
     )
 
-    llm = HuggingFacePipeline(pipeline = pipeline, model_kwargs = {'temperature':0.5,'repetition_penalty':1.1})
+    llm = HuggingFacePipeline(pipeline = pipeline, model_kwargs = {'temperature':0,'repetition_penalty':1.1})
 
     template = """Write a concise summary of the following:
                 "{text}"