Update app.py

app.py

@@ -1,42 +1,16 @@
 import streamlit as st
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import pipeline
 
-# Load model and tokenizer
-tokenizer = AutoTokenizer.from_pretrained("namannn/llama2-13b-hyperbolic-cluster-pruned")
-model = AutoModelForCausalLM.from_pretrained("namannn/llama2-13b-hyperbolic-cluster-pruned")
+sentiment_pipeline = pipeline("sentiment-analysis")
 
-# Streamlit UI components
-st.title("Text Generation with LLaMa2-13b Hyperbolic Model")
-st.write("Enter a prompt below and the model will generate text.")
+st.title("Sentiment Analysis with HuggingFace Spaces")
+st.write("Enter a sentence to analyze its sentiment:")
 
-# User input for prompt
-prompt = st.text_area("Input Prompt", "Once upon a time, in a land far away")
-
-# Slider for controlling the length of the output
-max_length = st.slider("Max Length of Generated Text", min_value=50, max_value=200, value=100)
-
-# Button to trigger text generation
-if st.button("Generate Text"):
-    if prompt:
-        # Encode the prompt text
-        inputs = tokenizer(prompt, return_tensors="pt")
-
-        # Generate text with the model
-        outputs = model.generate(
-            inputs["input_ids"],
-            max_length=max_length,
-            num_return_sequences=1,
-            no_repeat_ngram_size=2,  # You can tune this for diversity
-            do_sample=True,  # Use sampling for diverse generation
-            top_k=50,  # Top-k sampling for diversity
-            top_p=0.95,  # Top-p (nucleus) sampling
-            temperature=0.7  # Control randomness (lower = more deterministic)
-        )
-
-        # Decode and display generated text
-        generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
-        st.subheader("Generated Text:")
-        st.write(generated_text)
-    else:
-        st.warning("Please enter a prompt to generate text.")
+user_input = st.text_input("")
+if user_input:
+    result = sentiment_pipeline(user_input)
+    sentiment = result[0]["label"]
+    confidence = result[0]["score"]
 
+    st.write(f"Sentiment: {sentiment}")
+    st.write(f"Confidence: {confidence:.2f}")