Update backend.py

backend.py

@@ -1,6 +1,6 @@
 import time
 import torch
-from auto_gptq import AutoGPTQForCausalLM
+# from auto_gptq import AutoGPTQForCausalLM
 from huggingface_hub import hf_hub_download
 from langchain.chains import RetrievalQA
 from langchain.embeddings import HuggingFaceInstructEmbeddings
@@ -34,21 +34,21 @@ def load_model(model_id, model_basename=None):
                       "n_batch": max_ctx_size}
             return LlamaCpp(**kwargs)
 
-        else:
-            if ".safetensors" in model_basename:
-                model_basename = model_basename.replace(".safetensors", "")
-
-            tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
-
-            model = AutoGPTQForCausalLM.from_quantized(
-                model_id,
-                model_basename=model_basename,
-                use_safetensors=True,
-                trust_remote_code=True,
-                device="cuda:0",
-                use_triton=False,
-                quantize_config=None,
-            )
+        # else:
+        #     if ".safetensors" in model_basename:
+        #         model_basename = model_basename.replace(".safetensors", "")
+
+        #     tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
+
+        #     model = AutoGPTQForCausalLM.from_quantized(
+        #         model_id,
+        #         model_basename=model_basename,
+        #         use_safetensors=True,
+        #         trust_remote_code=True,
+        #         device="cuda:0",
+        #         use_triton=False,
+        #         quantize_config=None,
+        #     )
     else:
         tokenizer = AutoTokenizer.from_pretrained(model_id)