Update app.py

app.py

@@ -6,19 +6,19 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 import gradio as gr
 from threading import Thread
 
-model_id = "llm-jp/llm-jp-3-1.8b-instruct"
+model_id = "ibm-granite/granite-3.0-8b-instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
   model_id,
-  torch_dtype=torch.float16,
+  torch_dtype=torch.bfloat16,
   device_map="auto",
   use_flash_attention_2=True,
 )
 
-TITLE = "<h1><center>llm-jp/llm-jp-3-1.8b-instruct Chat webui</center></h1>"
+TITLE = "<h1><center>ibm-granite/granite-3.0-8b-instruct Chat webui</center></h1>"
 
 DESCRIPTION = """
-<h3>MODEL: <a href="https://huggingface.co/llm-jp/llm-jp-3-1.8b-instruct">llm-jp/llm-jp-3-1.8b-instruct</a></h3>
+<h3>MODEL: <a href="https://huggingface.co/ibm-granite/granite-3.0-8b-instruct">ibm-granite/granite-3.0-8b-instruct</a></h3>
 <center>
 <p>This model is designed for conversational interactions.</p>
 </center>