RaushanTurganbay HF staff commited on
Commit
9b91ee0
Β·
1 Parent(s): 5a9298b

change model

Browse files
Files changed (1) hide show
  1. app.py +3 -3
app.py CHANGED
@@ -31,8 +31,8 @@ bnb_config = BitsAndBytesConfig(
31
  bnb_4bit_compute_dtype=torch.bfloat16
32
  )
33
 
34
- tokenizer = AutoTokenizer.from_pretrained("lmsys/vicuna-13b-v1.3")
35
- model = AutoModelForCausalLM.from_pretrained("lmsys/vicuna-13b-v1.3", quantization_config=bnb_config, trust_remote_code=True, device_map="auto")
36
  if torch.__version__ >= "2":
37
  model = torch.compile(model)
38
  print(f"Successfully loaded the model {model_name} into memory")
@@ -179,7 +179,7 @@ with gr.Blocks(theme='gradio/soft') as demo:
179
  repetition_penalty = gr.Slider(label="Repetition Penalty", minimum=1.0, maximum=2.0, value=1.08, step=0.01)
180
 
181
  info = gr.HTML(f"""
182
- <p>🌐 Leveraging the <a href='https://huggingface.co/lmsys/vicuna-13b-v1.3'><strong>Vicuna model</strong></a> with int4 quantization.</p>
183
  """)
184
 
185
 
 
31
  bnb_4bit_compute_dtype=torch.bfloat16
32
  )
33
 
34
+ tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-7b1")
35
+ model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-7b1", device_map="auto")
36
  if torch.__version__ >= "2":
37
  model = torch.compile(model)
38
  print(f"Successfully loaded the model {model_name} into memory")
 
179
  repetition_penalty = gr.Slider(label="Repetition Penalty", minimum=1.0, maximum=2.0, value=1.08, step=0.01)
180
 
181
  info = gr.HTML(f"""
182
+ <p>🌐 Leveraging the <a href='https://huggingface.co/bigscience/bloomz-7b1'><strong>Vicuna model</strong></a> with int4 quantization.</p>
183
  """)
184
 
185