Spaces:
Sleeping
Sleeping
File size: 6,432 Bytes
be66a58 2b7c887 be66a58 7ce50b1 be66a58 7583b9e be66a58 12f4f82 be66a58 55b009f be66a58 b0af97b be66a58 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 |
import deepsparse
import gradio as gr
from typing import Tuple, List
deepsparse.cpu.print_hardware_capability()
MODEL_ID = "hf:neuralmagic/mpt-7b-gsm8k-pruned60-quant"
MAX_MAX_NEW_TOKENS = 1024
DEFAULT_MAX_NEW_TOKENS = 200
# Setup the engine
pipe = deepsparse.Pipeline.create(
task="text-generation",
model_path=MODEL_ID,
sequence_length=MAX_MAX_NEW_TOKENS,
prompt_sequence_length=16,
num_cores=8,
)
def clear_and_save_textbox(message: str) -> Tuple[str, str]:
return "", message
def display_input(
message: str, history: List[Tuple[str, str]]
) -> List[Tuple[str, str]]:
history.append((message, ""))
return history
def delete_prev_fn(history: List[Tuple[str, str]]) -> Tuple[List[Tuple[str, str]], str]:
try:
message, _ = history.pop()
except IndexError:
message = ""
return history, message or ""
with gr.Blocks() as demo:
with gr.Row():
with gr.Column():
gr.Markdown("""### MPT GSM Sparse Finetuned Demo""")
with gr.Group():
chatbot = gr.Chatbot(label="Chatbot")
with gr.Row():
textbox = gr.Textbox(container=False,placeholder="Type a message...",scale=10,)
submit_button = gr.Button("Submit", variant="primary", scale=1, min_width=0)
with gr.Row():
retry_button = gr.Button("🔄 Retry", variant="secondary")
undo_button = gr.Button("↩️ Undo", variant="secondary")
clear_button = gr.Button("🗑️ Clear", variant="secondary")
saved_input = gr.State()
gr.Examples(examples=[
"James decides to run 3 sprints 3 times a week. He runs 60 meters each sprint. How many total meters does he run a week?",
"Claire makes a 3 egg omelet every morning for breakfast. How many dozens of eggs will she eat in 4 weeks?",
"Gretchen has 110 coins. There are 30 more gold coins than silver coins. How many gold coins does Gretchen have?",],inputs=[textbox],)
# Generation inference
def generate(
message,
history,
max_new_tokens: int,
temperature: float,
top_p: float,
top_k: int,
repetition_penalty: float,
):
generation_config = { "max_new_tokens": max_new_tokens,"temperature": temperature,"top_p": top_p,"top_k": top_k,"repetition_penalty": repetition_penalty,}
inference = pipe(sequences=message, streaming=True, **generation_config)
history[-1][1] += message
for token in inference:
history[-1][1] += token.generations[0].text
yield history
print(pipe.timer_manager)
textbox.submit(
fn=clear_and_save_textbox,
inputs=textbox,
outputs=[textbox, saved_input],
api_name=False,
queue=False,
).then(
fn=display_input,
inputs=[saved_input, chatbot],
outputs=chatbot,
api_name=False,
queue=False,
).success(
generate,
inputs=[
saved_input,
chatbot,
max_new_tokens,
temperature,
top_p,
top_k,
repetition_penalty,
],
outputs=[chatbot],
api_name=False,
)
submit_button.click(
fn=clear_and_save_textbox,
inputs=textbox,
outputs=[textbox, saved_input],
api_name=False,
queue=False,
).then(
fn=display_input,
inputs=[saved_input, chatbot],
outputs=chatbot,
api_name=False,
queue=False,
).success(
generate,
inputs=[saved_input, chatbot, max_new_tokens, temperature],
outputs=[chatbot],
api_name=False,
)
retry_button.click(
fn=delete_prev_fn,
inputs=chatbot,
outputs=[chatbot, saved_input],
api_name=False,
queue=False,
).then(
fn=display_input,
inputs=[saved_input, chatbot],
outputs=chatbot,
api_name=False,
queue=False,
).then(
generate,
inputs=[saved_input, chatbot, max_new_tokens, temperature],
outputs=[chatbot],
api_name=False,
)
undo_button.click(
fn=delete_prev_fn,
inputs=chatbot,
outputs=[chatbot, saved_input],
api_name=False,
queue=False,
).then(
fn=lambda x: x,
inputs=[saved_input],
outputs=textbox,
api_name=False,
queue=False,
)
clear_button.click(
fn=lambda: ([], ""),
outputs=[chatbot, saved_input],
queue=False,
api_name=False,
)
demo.queue().launch()
|