Update app.py

app.py

@@ -42,9 +42,9 @@ def redistribute_codes(row):
 snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz").to("cuda")
 
 # Load the single-speaker language model
-tokenizer = AutoTokenizer.from_pretrained('Llama-3B-Mono-Jim')
+tokenizer = AutoTokenizer.from_pretrained('prithivMLmods/Llama-3B-Mono-Jim')
 model = AutoModelForCausalLM.from_pretrained(
-    'Llama-3B-Mono-Jim', torch_dtype=torch.bfloat16
+    'prithivMLmods/Llama-3B-Mono-Jim', torch_dtype=torch.bfloat16
 ).cuda()
 
 @spaces.GPU
@@ -76,7 +76,7 @@ def generate_audio(text, temperature, top_p, max_new_tokens):
 # Gradio Interface
 with gr.Blocks() as demo:
     gr.Markdown("# Llama-3B-Mono-Jim - Single Speaker Audio Generation")
-    gr.Markdown("Generate speech audio using the `Llama-3B-Mono-Jim` model.")
+    gr.Markdown("Generate speech audio using the `prithivMLmods/Llama-3B-Mono-Jim` model.")
     
     with gr.Row():
         text_input = gr.Textbox(lines=4, label="Input Text")