Update app.py

app.py

@@ -21,14 +21,15 @@ from langchain import PromptTemplate, LLMChain
 model_name_or_path = "hlhr202/llama-7B-ggml-int4"
 model_basename = "ggml-model-q4_0.bin" # the model is in bin format
 
-model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)
+#model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)
 
 n_gpu_layers = 40 # Change this value based on your model and your GPU VRAM pool.
 n_batch = 256 
 
-llm = LlamaCpp(
-    model_path=model_path, callbacks=[StreamingStdOutCallbackHandler()]
-)
+llm = LLM = G4FLLM(
+        model=models.gpt_35_turbo,
+        provider=Provider.Acytoo,
+    )
 
 #llm = LLM = G4FLLM(model=models.gpt_35_turbo,provider=Provider.DeepAi,)