Update app.py

app.py

@@ -9,8 +9,8 @@ from huggingface_hub import hf_hub_download
 
 llm = Llama(
     model_path=hf_hub_download(
-        repo_id=os.environ.get("REPO_ID", "TheBloke/Llama-2-7b-Chat-GGUF"),
-        filename=os.environ.get("MODEL_FILE", "llama-2-7b-chat.Q5_0.gguf"),
+        repo_id=os.environ.get("REPO_ID", "Severian/ANIMA-Phi-Neptune-Mistral-7B-gguf"),
+        filename=os.environ.get("MODEL_FILE", "anima-phi-neptune-mistral-7b.Q4_K_M.gguf"),
     ),
     n_ctx=2048,
     n_gpu_layers=50, # change n_gpu_layers if you have more or less VRAM 
@@ -60,13 +60,12 @@ def generate_text(message, history):
 
 demo = gr.ChatInterface(
     generate_text,
-    title="llama-cpp-python on GPU",
-    description="Running LLM with https://github.com/abetlen/llama-cpp-python",
-    examples=["tell me everything about llamas"],
+    title="A N I M A",
+    description="ANIMA is an expert in various scientific disciplines.",
+    examples=["tell me everything about biomimicry"],
     cache_examples=True,
     retry_btn=None,
     undo_btn="Delete Previous",
     clear_btn="Clear",
-    
 )
 demo.launch(max_threads=10)