Update app.py

app.py

@@ -1,17 +1,19 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from transformers import pipeline
-
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-import gradio as gr
+# Load the model and tokenizer manually
+model_name = "BeastGokul/Bio-Medical-MultiModal-Llama-3-8B-Finetuned"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
+# Create a pipeline using the manually loaded model and tokenizer
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
-# Initialize the pipeline with your fine-tuned biomedical model
-pipe = pipeline("text-generation", model="BeastGokul/Bio-Medical-MultiModal-Llama-3-8B-Finetuned")
 
 def generate_response(chat_history, max_length, temperature, top_p):
     conversation = "\n".join([f"User: {msg[0]}\nModel: {msg[1]}" for msg in chat_history if msg[1]])