change model file and using ctransformers directly instead of langchain.

app.py

@@ -8,8 +8,8 @@ from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 # from langchain.llms import LlamaCpp
 from langchain.vectorstores import Qdrant
 from qdrant_client.http import models
-from langchain.llms import CTransformers
-# from ctransformers import AutoModelForCausalLM
+# from langchain.llms import CTransformers
+from ctransformers import AutoModelForCausalLM
 
 
 
@@ -36,13 +36,13 @@ print("loading the LLM......................................")
 # verbose=True,
 # )
 
-llm = CTransformers(
- model="TheBloke/Llama-2-7B-Chat-GGUF/llama-2-7b-chat.Q8_0.gguf", 
- callbacks=[StreamingStdOutCallbackHandler()],
- temperature = 0.2,
- max_new_tokens = 1000,
- 
-)
+llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGUF", 
+ model_file="llama-2-7b-chat.Q8_0.gguf", 
+ model_type="llama", 
+ # config = ctransformers.hub.AutoConfig,
+ hf = True
+ )
+
 
 
 print("LLM loaded........................................")