Spaces:
Sleeping
Sleeping
from huggingface_hub import InferenceClient | |
import gradio as gr | |
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1") | |
additional_inputs=[ | |
gr.Textbox( | |
label="System Prompt", | |
max_lines=1, | |
interactive=True, | |
), | |
gr.Slider( | |
label="Temperature", | |
value=0.2, | |
minimum=0.0, | |
maximum=1.0, | |
step=0.05, | |
interactive=True, | |
info="Higher values produce more diverse outputs", | |
), | |
gr.Slider( | |
label="Max new tokens", | |
value=512, | |
minimum=0, | |
maximum=1048, | |
step=64, | |
interactive=True, | |
info="The maximum numbers of new tokens", | |
), | |
gr.Slider( | |
label="Top-p (nucleus sampling)", | |
value=0.95, | |
minimum=0.0, | |
maximum=1, | |
step=0.05, | |
interactive=True, | |
info="Higher values sample more low-probability tokens", | |
), | |
gr.Slider( | |
label="Repetition penalty", | |
value=1, | |
minimum=1.0, | |
maximum=2.0, | |
step=0.05, | |
interactive=True, | |
info="Penalize repeated tokens", | |
) | |
] | |
mychatbot = gr.Chatbot( | |
avatar_images=["./user.png", "./botm.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=False) | |