Fixed path

app.py

@@ -31,7 +31,7 @@ login(token=hf_token)
 sentence_transformer_model = "all-MiniLM-L6-v2"
 # Upgrade to the 8B model and choose Q4_0 quantization for a good balance of performance and resource usage.
 repo_id = "bartowski/deepcogito_cogito-v1-preview-llama-8B-GGUF"
-filename = "deepcogito_cogito-v1-preview-llama-8B-Q4_KM.gguf"  # New 8B model with Q4_0 quantization
+filename = "deepcogito_cogito-v1-preview-llama-8B-Q4_K_M.gguf"  # New 8B model with Q4_0 quantization
 
 # Define FAQs (unchanged)
 faqs = [
@@ -175,7 +175,7 @@ async def model_info():
     return {
         "model_name": "deepcogito_cogito-v1-preview-llama-8B-GGUF",
         "model_size": "8B",
-        "quantization": "Q4_KM",
+        "quantization": "Q4_K_M",
         "embedding_model": sentence_transformer_model,
         "faiss_index_size": len(cv_chunks),
         "faiss_index_dim": cv_embeddings.shape[1],