Update app.py

app.py

@@ -5,7 +5,6 @@
 
 import sys
 import os
-import torch
 import transformers
 import json
 
@@ -14,18 +13,6 @@ assert (
 ), "Please reinstall it: pip uninstall transformers && pip install git+https://github.com/huggingface/transformers.git"
 from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig
 
-if torch.cuda.is_available():
-    device = "cuda"
-else:
-    device = "cpu"
-
-try:
-    if torch.backends.mps.is_available():
-        device = "mps"
-except:
-    pass
-
-
 base_model = "https://huggingface.co/Shangding-Gu/Lunyu-LLM/"
 
 tokenizer = LlamaTokenizer.from_pretrained(base_model)
@@ -48,11 +35,6 @@ model.config.pad_token_id = tokenizer.pad_token_id = 0  # unk
 model.config.bos_token_id = 1
 model.config.eos_token_id = 2
 
-if not load_8bit:
-    model.half()  # seems to fix bugs for some users.
-if torch.__version__ >= "2" and sys.platform != "win32":
-            model = torch.compile(model)
-
 class Call_model():
     model.eval()
     def evaluate(self, instruction):
@@ -84,8 +66,7 @@ class Call_model():
             num_beams=num_beams,
             **kwargs,
         )
-        with torch.no_grad():
-            generation_output = model.generate(
+        generation_output = model.generate(
                 input_ids=input_ids,
                 generation_config=generation_config,
                 return_dict_in_generate=True,