Update app.py

app.py

@@ -9,7 +9,7 @@ import os
 # Install flash-attn
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 # Initialize the model pipeline
-generator = pipeline('text-generation', model='Locutusque/Hyperion-1.5-Mistral-7B', torch_dtype=torch.bfloat16, token=os.environ["HF"])
+generator = pipeline('text-generation', model='M4-ai/tau-0.5B', torch_dtype=torch.bfloat16)
 @spaces.GPU
 def generate_text(prompt, temperature, top_p, top_k, repetition_penalty, max_length):
     # Generate text using the model
@@ -35,7 +35,7 @@ def generate_text(prompt, temperature, top_p, top_k, repetition_penalty, max_len
 iface = gr.Interface(
     fn=generate_text,
     inputs=[
-        gr.Textbox(label="Prompt", lines=2, placeholder="Type a prompt..."),
+        gr.Textbox(label="Prompt", lines=2, value="Write me a Python program that calculates the factorial of a given number."),
         gr.Slider(minimum=0.1, maximum=2.0, step=0.01, value=0.8, label="Temperature"),
         gr.Slider(minimum=0.0, maximum=1.0, step=0.01, value=0.95, label="Top p"),
         gr.Slider(minimum=0, maximum=100, step=1, value=40, label="Top k"),
@@ -43,8 +43,8 @@ iface = gr.Interface(
         gr.Slider(minimum=5, maximum=4096, step=5, value=1024, label="Max Length")
     ],
     outputs=gr.Textbox(label="Generated Text"),
-    title="Hyperion-1.5-Mistral-7B",
-    description="Try out the Hyperion-1.5-Mistral-7B model for free! This is a preview version, and the model will be released soon"
+    title="M4-ai/tau-0.5B",
+    description="Try out the M4-ai/tau-0.5B model for free!"
 )
 
 iface.launch()