updates

app.py

@@ -2,17 +2,15 @@ import gradio as gr
 from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 
-# ✅ Download GGUF file
 model_path = hf_hub_download(
     repo_id="jerinaj/lfm-tool",
-    filename="lfm-tool.Q4_K_M.gguf"  # 👈 IMPORTANT: exact filename
+    filename="LFM2-350M.Q4_K_M.gguf"
 )
 
-# ✅ Load model
 llm = Llama(
     model_path=model_path,
-    n_ctx=2048,
-    n_threads=4
+    n_ctx=1024,
+    n_threads=2
 )
 
 def chat(prompt):