Update app.py

app.py

@@ -1,34 +1,21 @@
-import sys
 import streamlit as st
-
-HF_API_TOKEN = "your_huggingface_api_token_here"  # <-- paste your token
-MODEL_ID = "mistralai/Mistral-7B-Instruct-v0.2"
-API_URL = f"https://api-inference.huggingface.co/models/{MODEL_ID}"
-HEADERS = {"Authorization": f"Bearer {HF_API_TOKEN}"}
-
-import streamlit as st
-from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig
 import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-st.title("📚 AI Adaptive Learning (Local Small Model)")
+st.title("📚 AI Adaptive Learning")
 
-MODEL_ID = "microsoft/phi-2"
+MODEL_ID = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
 
 @st.cache_resource
 def load_model():
-    tokenizer = AutoTokenizer.from_pretrained(
-        MODEL_ID,
-        trust_remote_code=True
-    )
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 
     if tokenizer.pad_token is None:
         tokenizer.pad_token = tokenizer.eos_token
 
     model = AutoModelForCausalLM.from_pretrained(
         MODEL_ID,
-        trust_remote_code=True,
-        torch_dtype=torch.float32   # CPU safe
-        # ❌ removed device_map="auto"
+        torch_dtype=torch.float32
     )
 
     model.eval()
@@ -36,21 +23,22 @@ def load_model():
 
 tokenizer, model = load_model()
 
-# Input question
 user_input = st.text_input("Ask a question:")
 
 if st.button("Submit") and user_input:
-    inputs = tokenizer(user_input, return_tensors="pt")
-
-    with torch.no_grad():
-        outputs = model.generate(
-            **inputs,
-            max_new_tokens=150,
-            do_sample=True,
-            temperature=0.7
-        )
-
-    answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    with st.spinner("Generating answer..."):
+        inputs = tokenizer(user_input, return_tensors="pt")
+
+        with torch.no_grad():
+            outputs = model.generate(
+                **inputs,
+                max_new_tokens=150,
+                temperature=0.7,
+                do_sample=True,
+                pad_token_id=tokenizer.eos_token_id
+            )
+
+        answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
     st.subheader("AI Answer:")
     st.write(answer)