Update app.py

app.py

@@ -9,7 +9,7 @@ import chromadb
 import os
 import requests
 
-API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-2-7b-chat-hf"
+API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-2-7b-hf"
 headers = {"Authorization": f"Bearer {os.getenv('HF_Token')}"}
 
 def query_llama(prompt):
@@ -40,7 +40,7 @@ def get_embedding(text):
     return outputs.last_hidden_state[:, 0, :].numpy().tolist()  # Take CLS token embedding
 
 # Load LLaMA Model (Meta LLaMA 2)
-llama_pipe = pipeline("text-generation", model=AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf"))
+#llama_pipe = pipeline("text-generation", model=AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf"))
 
 # Load a small subset (10,000 rows)
 #dataset = load_dataset("wiki40b", "en", split="train[:1000]")