Spaces:
Runtime error
Runtime error
File size: 4,074 Bytes
9255bb8 b1f91f1 9255bb8 b1f91f1 9255bb8 9ded88b 9255bb8 b1f91f1 9255bb8 040a3f3 9255bb8 b1f91f1 da6c800 d7c0687 9255bb8 b1f91f1 9255bb8 b1f91f1 9255bb8 de17bac 9255bb8 7926189 9255bb8 9ded88b 9255bb8 |
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 |
import json
import os
import shutil
import gradio as gr
from huggingface_hub import Repository
from text_generation import Client
from share_btn import community_icon_html, loading_icon_html, share_js, share_btn_css
HF_TOKEN = os.environ.get("HF_TOKEN", None)
API_URL = os.environ.get("API_URL")
theme = gr.themes.Monochrome(
primary_hue="indigo",
secondary_hue="blue",
neutral_hue="slate",
radius_size=gr.themes.sizes.radius_sm,
font=[gr.themes.GoogleFont("Open Sans"), "ui-sans-serif", "system-ui", "sans-serif"],
)
client = Client(
API_URL,
#headers={"Authorization": f"Bearer {HF_TOKEN}"},
)
def generate(prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
temperature = float(temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(top_p)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=max_new_tokens,
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
truncate=999,
seed=42,
stop_sequences=["</s>"],
)
stream = client.generate_stream(
prompt,
**generate_kwargs,
)
output = prompt
for response in stream:
output += response.token.text
yield output
return output
examples = [
"def hello_world():",
"def fibonacci(n):",
"class TransformerDecoder(nn.Module):",
"class ComplexNumbers:"
]
def process_example(args):
for x in generate(args):
pass
return x
css = ".generating {visibility: hidden}" + share_btn_css
with gr.Blocks(theme=theme, analytics_enabled=False, css=css) as demo:
with gr.Column():
gr.Markdown(
""" # BigCode - Playground
"""
)
with gr.Row():
with gr.Column(scale=3):
instruction = gr.Textbox(placeholder="Enter your prompt here", label="Prompt", elem_id="q-input")
with gr.Box():
output = gr.Code(elem_id="q-output")
submit = gr.Button("Generate", variant="primary")
gr.Examples(
examples=examples,
inputs=[instruction],
cache_examples=False,
fn=process_example,
outputs=[output],
)
with gr.Column(scale=1):
temperature = gr.Slider(
label="Temperature",
value=0.2,
minimum=0.0,
maximum=2.0,
step=0.1,
interactive=True,
info="Higher values produce more diverse outputs",
)
max_new_tokens = gr.Slider(
label="Max new tokens",
value=256,
minimum=0,
maximum=512,
step=4,
interactive=True,
info="The maximum numbers of new tokens",
)
top_p = gr.Slider(
label="Top-p (nucleus sampling)",
value=0.90,
minimum=0.0,
maximum=1,
step=0.05,
interactive=True,
info="Higher values sample more low-probability tokens",
)
repetition_penalty = gr.Slider(
label="Repetition penalty",
value=1.2,
minimum=1.0,
maximum=2.0,
step=0.05,
interactive=True,
info="Penalize repeated tokens",
)
submit.click(generate, inputs=[instruction, temperature, max_new_tokens, top_p, repetition_penalty], outputs=[output])
instruction.submit(generate, inputs=[instruction, temperature, max_new_tokens, top_p, repetition_penalty], outputs=[output])
demo.queue(concurrency_count=16).launch(debug=True) |