Update app.py

app.py

@@ -1,5 +1,6 @@
 
 from langchain_community.llms import CTransformers
+from ctransformers import AutoModelForCausalLM
 from langchain.agents import Tool
 from langchain.agents import AgentType, initialize_agent
 from langchain.chains import RetrievalQA
@@ -74,13 +75,14 @@ def main():
                     # 'threads': int(os.cpu_count() / 2)
                     # }
                         
-                    llm = CTransformers(
-                    # model = "TheBloke/Mistral-7B-Instruct-v0.2-GGUF",
-                    model= "TheBloke/phi-2-GGUF",
-                    model_type="mistral",
-                    max_new_tokens = 1048,
-                    temperature = 0.3
-                    )
+                    # llm = CTransformers(
+                    # # model = "TheBloke/Mistral-7B-Instruct-v0.2-GGUF",
+                    # model= "TheBloke/phi-2-GGUF",
+                    # model_type="mistral",
+                    # max_new_tokens = 1048,
+                    # temperature = 0.3
+                    # )
+                    llm = AutoModelForCausalLM.from_pretrained("/path/to/ggml-model.bin")
                         
                     print("LLM Initialized...")