Adding a simple monkey search for Leetcode - Darn LeetMonkey

app.py

@@ -6,6 +6,28 @@ from sentence_transformers import SentenceTransformer
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import os
 
+import requests
+import os
+from tqdm import tqdm
+
+
+def download_model(url, model_path):
+    response = requests.get(url, stream=True)
+    total_size = int(response.headers.get('content-length', 0))
+    block_size = 1024  # 1 KB
+
+    with open(model_path, 'wb') as file, tqdm(
+        desc=model_path,
+        total=total_size,
+        unit='iB',
+        unit_scale=True,
+        unit_divisor=1024,
+    ) as progress_bar:
+        for data in response.iter_content(block_size):
+            size = file.write(data)
+            progress_bar.update(size)
+
+
 # Initialize Pinecone
 PINECONE_API_KEY = os.environ.get('PINECONE_API_KEY')
 pc = Pinecone(api_key=PINECONE_API_KEY)
@@ -17,10 +39,21 @@ device = 'cpu'
 splade = SpladeEncoder(device=device)
 dense_model = SentenceTransformer('sentence-transformers/all-Mpnet-base-v2', device=device)
 
-# Load the quantized Llama 2 model and tokenizer
-model_name = "distilgpt2"  # Using distilgpt2 for CPU efficiency
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, low_cpu_mem_usage=True)
+from llama_cpp import Llama
+
+# Define the model URL and path
+model_url = "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q4_K_M.gguf"
+model_path = "/tmp/llama-2-7b-chat.Q4_K_M.gguf"
+
+# Download the model if it doesn't exist
+if not os.path.exists(model_path):
+    print(f"Downloading model to {model_path}...")
+    download_model(model_url, model_path)
+    print("Model downloaded successfully.")
+
+# Initialize the Llama model
+llm = Llama(model_path=model_path, n_ctx=2048, n_threads=4)
+
 
 def search_problems(query, top_k=5):
     dense_query = dense_model.encode([query])[0].tolist()

requirements.txt

@@ -6,4 +6,5 @@ sentence-transformers==2.2.2
 pinecone-text
 accelerate
 optimum
-auto-gptq
+auto-gptq
+llama-cpp-python