Update app.py

app.py

@@ -64,10 +64,10 @@ quant_config = BitsAndBytesConfig(
 )
 
 #config = PeftConfig.from_pretrained("physician-ai/mistral-finetuned1",use_auth_token=access_token)
-model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2",use_auth_token=access_token,quantization_config=quant_config,device_map="auto")
-model = PeftModel.from_pretrained(model, "physician-ai/mistral-finetuned1",use_auth_token=access_token)
-tokenizer = AutoTokenizer.from_pretrained("physician-ai/mistral-finetuned1",use_auth_token=access_token)
-text_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=1024, temperature=0.8, top_p=0.95, repetition_penalty=1.15)
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B",use_auth_token=access_token,quantization_config=quant_config,device_map="auto")
+model = PeftModel.from_pretrained(model, "physician-ai/llama3-8b-finetuned",use_auth_token=access_token,quantization_config=quant_config,device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("physician-ai/llama3-8b-finetuned",use_auth_token=access_token)
+text_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=4096, temperature=0.8, top_p=0.95, repetition_penalty=1.15)
 
 terminators = [
     tokenizer.eos_token_id,
@@ -120,7 +120,7 @@ chatbot=gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterf
 with gr.Blocks(fill_height=True, css=css) as demo:
     
     gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(value="Used Finetuned Mistral 7B Model", elem_id="duplicate-button")
+    gr.DuplicateButton(value="Finetuned LLAMA 3 8B Model", elem_id="duplicate-button")
     gr.ChatInterface(
         fn=chat_llama3_8b,
         chatbot=chatbot,