Spaces:
Running
on
Zero
Running
on
Zero
File size: 3,783 Bytes
f9e7dbf 49fba9e f9e7dbf 49fba9e f9e7dbf 49fba9e f9e7dbf 49fba9e f9e7dbf 49fba9e f9e7dbf 49fba9e f9e7dbf 49fba9e f9e7dbf 49fba9e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
import spaces
import gradio as gr
from huggingface_hub import InferenceClient
from vptq.app_utils import get_chat_loop_generator
# Update model list with annotations
model_list_with_annotations = {
# "VPTQ-community/Meta-Llama-3.1-70B-Instruct-v8-k65536-65536-woft": "Llama 3.1 70B @ 4bit",
# "VPTQ-community/Meta-Llama-3.1-70B-Instruct-v8-k65536-256-woft": "Llama 3.1 70B @ 3bit",
# "VPTQ-community/Meta-Llama-3.1-70B-Instruct-v16-k65536-65536-woft": "Llama 3.1 70B @ 2bit",
# "VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-65536-woft": "Qwen2.5 72B @ 4 bits",
# "VPTQ-community/Qwen2.5-72B-Instruct-v8-k65536-256-woft": "Qwen2.5 72B @ 3 bits",
# "VPTQ-community/Qwen2.5-72B-Instruct-v16-k65536-65536-woft": "Qwen2.5 72B @ 3 bits",
# "VPTQ-community/Qwen2.5-32B-Instruct-v8-k65536-65536-woft": "Qwen2.5 32B @ 4 bits",
"VPTQ-community/Qwen2.5-32B-Instruct-v8-k65536-256-woft": "Qwen2.5 32B @ 3 bits",
"VPTQ-community/Qwen2.5-32B-Instruct-v16-k65536-0-woft": "Qwen2.5 32B @ 2 bits"
}
# Create a list of choices with annotations for the dropdown
model_list_with_annotations_display = [f"{key} ({value})" for key, value in model_list_with_annotations.items()]
model_keys = list(model_list_with_annotations.keys())
current_model_g = model_keys[0]
chat_completion = get_chat_loop_generator(current_model_g)
@spaces.GPU
def update_title_and_chatmodel(model):
model = str(model)
global chat_completion
global current_model_g
if model != current_model_g:
current_model_g = model
chat_completion = get_chat_loop_generator(current_model_g)
return model
@spaces.GPU
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
for message in chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message
response += token
yield response
css = """
h1 {
text-align: center;
display: block;
}
"""
chatbot = gr.Chatbot(label="Gradio ChatInterface")
with gr.Blocks() as demo:
with gr.Column(scale=1):
title_output = gr.Markdown("Please select a model to run")
chat_demo = gr.ChatInterface(
respond,
additional_inputs_accordion=gr.Accordion(
label="⚙️ Parameters", open=False, render=False
),
fill_height=False,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)"
),
],
)
model_select = gr.Dropdown(
choices=model_list_with_annotations_display,
label="Models",
value=model_list_with_annotations_display[0],
info="Model & Estimated Quantized Bitwidth"
)
model_select.change(update_title_and_chatmodel, inputs=[model_select], outputs=title_output)
if __name__ == "__main__":
demo.launch() |