Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -313,7 +313,7 @@ with gr.Blocks(css=custom_css) as demo:
|
|
313 |
highlight_EaInfer = gr.Checkbox(label="Highlight the tokens generated by EAGLE-2", value=True)
|
314 |
temperature = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="temperature", value=0.5)
|
315 |
top_p = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="top_p", value=0.9)
|
316 |
-
note=gr.Markdown(show_label=False,value='''The original LLM is LLaMA3-Instruct 8B, running on
|
317 |
will be displayed in orange. Note: Checking this option may cause special formatting rendering issues in a few cases, especially when generating code''')
|
318 |
|
319 |
|
|
|
313 |
highlight_EaInfer = gr.Checkbox(label="Highlight the tokens generated by EAGLE-2", value=True)
|
314 |
temperature = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="temperature", value=0.5)
|
315 |
top_p = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="top_p", value=0.9)
|
316 |
+
note=gr.Markdown(show_label=False,value='''The original LLM is LLaMA3-Instruct 8B, running on ZERO. The Compression Ratio is defined as the number of generated tokens divided by the number of forward passes in the original LLM. If "Highlight the tokens generated by EAGLE-2" is checked, the tokens correctly guessed by EAGLE-2
|
317 |
will be displayed in orange. Note: Checking this option may cause special formatting rendering issues in a few cases, especially when generating code''')
|
318 |
|
319 |
|