minhdang commited on
Commit
92debe5
·
verified ·
1 Parent(s): e3d40f2

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -15,7 +15,7 @@ nf4_config = BitsAndBytesConfig(
15
 
16
  model_id = "yunconglong/MoE_13B_DPO"
17
  tokenizer = AutoTokenizer.from_pretrained(model_id)
18
- model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=nf4_config)
19
 
20
  @spaces.GPU
21
  def generate_response(user_input, max_new_tokens, temperature):
 
15
 
16
  model_id = "yunconglong/MoE_13B_DPO"
17
  tokenizer = AutoTokenizer.from_pretrained(model_id)
18
+ model = AutoModelForCausalLM.from_pretrained(model_id, load_in_8bit=True)
19
 
20
  @spaces.GPU
21
  def generate_response(user_input, max_new_tokens, temperature):