Xenova HF staff commited on
Commit
7a4d62a
1 Parent(s): a347490

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +0 -2
app.py CHANGED
@@ -7,7 +7,6 @@ import spaces
7
  import torch
8
  from transformers import (
9
  AutoModelForCausalLM,
10
- BitsAndBytesConfig,
11
  GemmaTokenizerFast,
12
  TextIteratorStreamer,
13
  )
@@ -34,7 +33,6 @@ model = AutoModelForCausalLM.from_pretrained(
34
  model_id,
35
  device_map="auto",
36
  torch_dtype=torch.bfloat16,
37
- quantization_config=BitsAndBytesConfig(load_in_8bit=True),
38
  )
39
  model.config.sliding_window = 4096
40
  model.eval()
 
7
  import torch
8
  from transformers import (
9
  AutoModelForCausalLM,
 
10
  GemmaTokenizerFast,
11
  TextIteratorStreamer,
12
  )
 
33
  model_id,
34
  device_map="auto",
35
  torch_dtype=torch.bfloat16,
 
36
  )
37
  model.config.sliding_window = 4096
38
  model.eval()