Update app.py

app.py

@@ -10,12 +10,12 @@ from huggingface_hub import upload_file
 import json
 from uuid import uuid4
 
-model_id = "Elijahbodden/eliGPTv1.1"
+model_id = "Elijahbodden/eliGPTv1.3"
 
 # MODEL
 model = Llama.from_pretrained(
     repo_id=model_id,
-    filename="eliGPTv1.1-unsloth.Q5_K_M.gguf",
+    filename="model.gguf",
     verbose=True,
     n_threads = 2,
     n_threads_batch = 2,
@@ -73,7 +73,7 @@ def respond(
         stop=["<|im_end|>"],
         min_p=min_p,
         max_tokens=max_tokens,
-        # Disable top-p pruning
+        # Disable top-k pruning
         top_k=100000000,
         frequency_penalty=frequency_penalty,
         presence_penalty=presence_penalty,
@@ -90,7 +90,7 @@ demo = gr.ChatInterface(
     additional_inputs_accordion=gr.Accordion(label="Options", open=True),
     css=".bubble-gap {gap: 6px !important}",
     theme="shivi/calm_seafoam",
-    description="The model may take a while if it hasn't run recently or a lot of people are using it",
+    description="The model may be slow if it hasn't run recently or a lot of people are using it",
     title="EliGPT v1.3",
     additional_inputs=[
         gr.Radio(presets.keys(), label="Personality preset", info="VERY SLIGHTLY influence the model's personality [WARNING, IF YOU CHANGE THIS WHILE THERE ARE MESSAGES IN THE CHAT, THE MODEL WILL BECOME VERY SLOW]", value="Default"),