Update app.py

app.py

@@ -16,11 +16,11 @@ nf4_config = BitsAndBytesConfig(
    bnb_4bit_compute_dtype=torch.bfloat16
 )
 
-model_id = "Qwen/Qwen1.5-14B-Chat"
+model_id = "CohereForAI/c4ai-command-r-v01"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id,
                                              # load_in_8bit=True,
-                                             # quantization_config=nf4_config
+                                             quantization_config=nf4_config
                                              torch_dtype = torch.bfloat16,
                                              device_map="auto"
                                             )