Update app.py

app.py

@@ -27,13 +27,13 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # model_id = "mistralai/Mistral-7B-v0.3"
 
-model_id = "CohereForAI/c4ai-command-r-plus"
+model_id = "CohereForAI/c4ai-command-r-plus-4bit"
 
 
 tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)
 
 model = AutoModelForCausalLM.from_pretrained(model_id, token= token, 
-                                                 torch_dtype=torch.bfloat16,    
+                                                 # torch_dtype=torch.bfloat16,    
                                              attn_implementation="flash_attention_2",
                                              # low_cpu_mem_usage=True,
                                              # llm_int8_enable_fp32_cpu_offload=True,