Update app.py

app.py

@@ -1,9 +1,21 @@
 import requests
 import streamlit as st
-from together import Together
+import torch
+from transformers import pipeline
 
-# Initialize Together AI client
-client = Together(api_key=st.secrets["TOGETHER_API_KEY"])
+# Initialize Llama 3.2 model
+@st.cache_resource
+def load_model():
+    model_id = "meta-llama/Llama-3.2-1B"
+    pipe = pipeline(
+        "text-generation", 
+        model=model_id, 
+        torch_dtype=torch.bfloat16, 
+        device_map="auto"
+    )
+    return pipe
+
+pipe = load_model()
 
 def call_llama_for_response(clauses_data):
     prompt = "As an AI assistant specializing in contract analysis, draft a professional and courteous response to a contract drafter based on the following clause analyses and decisions:\n\n"
@@ -19,18 +31,8 @@ def call_llama_for_response(clauses_data):
     
     prompt += "Draft a response that addresses each clause, explaining our position on acceptance, rejection, or negotiation. The tone should be professional, courteous, and constructive."
 
-    response = client.chat.completions.create(
-        model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
-        messages=[{"role": "user", "content": prompt}],
-        max_tokens=2048,
-        temperature=0.3,
-        top_p=0.8,
-        top_k=50,
-        repetition_penalty=1,
-        stop=["<|eot_id|>", "<|eom_id|>"],
-        stream=False
-    )
-    return response.choices[0].message.content
+    response = pipe(prompt, max_new_tokens=500, do_sample=True, temperature=0.7)
+    return response[0]['generated_text']
 
 st.title("Contract Negotiation Assistant")