Update app.py

app.py

@@ -21,15 +21,14 @@ nf4_config = BitsAndBytesConfig(
    bnb_4bit_use_double_quant=True,
    bnb_4bit_compute_dtype=torch.bfloat16
 )
-
 model_id = "CohereForAI/c4ai-command-r-v01"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained("c4ai-command-r-v01-exl2",
+model = AutoModelForCausalLM.from_pretrained(model_id,
                                              # load_in_8bit=True,
-                                             #quantization_config=nf4_config,
+                                             quantization_config=nf4_config,
                                             # attn_implementation="flash_attention_2",
                                              # torch_dtype = torch.bfloat16,
-                                             #device_map="auto"
+                                             device_map="auto"
                                             )
 
 # replace_linears_in_hf(model)