added folders

app.py

@@ -1,24 +1,29 @@
 import streamlit as st
-import requests
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
-# API details
-API_URL = "https://api-inference.huggingface.co/models/MudassirFayaz/career_councling_using_bart"
-headers = {"Authorization": "Bearer "}
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained('tokenizer-llama_career_0.5.0')
+model = AutoModelForCausalLM.from_pretrained('llama-2-7b-career-0.5.0', 
+                                             adapter_name_or_path='path/to/model/folder/adapter_model.bin')
 
-
-def query(payload):
-    response = requests.post(API_URL, headers=headers, json=payload)
-    return response.json()
+# Function to generate response
+def generate_response(input_text):
+    inputs = tokenizer(input_text, return_tensors='pt')
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_length=50, do_sample=True)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
 
 # Streamlit app
-st.title("Career Counseling using BART")
-st.write("Enter a prompt and get a response from the BART model for career counseling.")
+st.title("Hugging Face Model Chatbot")
+st.write("Interact with your custom model")
 
-# User input
-user_input = st.text_area("Enter your prompt here:", "The answer to the universe is")
+input_text = st.text_input("You:", "")
 
-if st.button("Get Response"):
-    with st.spinner("Querying the API..."):
-        output = query({"inputs": user_input})
-        st.success("Response received!")
-        st.write("**Output:**", output)
+if st.button("Generate Response"):
+    if input_text:
+        response = generate_response(input_text)
+        st.write(f"Model: {response}")
+    else:
+        st.write("Please enter some text.")