Spaces:
Runtime error
Runtime error
File size: 4,769 Bytes
a865a75 |
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 |
import gradio as gr
import time
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
model = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.1-GGUF", model_file="mistral-7b-instruct-v0.1.Q5_K_S.gguf", model_type="mistral", gpu_layers=0)
ins = '''[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>
{} [/INST]
'''
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"],
)
def response(question):
start_time = time.time()
res = model(ins.format(question))
end_time = time.time()
yield {'inference_time': end_time - start_time,'response':res}
examples = [
"Instead of making a peanut butter and jelly sandwich, what else could I combine peanut butter with in a sandwich? Give five ideas",
"How do I make a campfire?",
"Explain to me the difference between nuclear fission and fusion.",
"I'm selling my Nikon D-750, write a short blurb for my ad."
]
def process_example(args):
for x in generate(args):
pass
return x
css = ".generating {visibility: hidden}"
# Based on the gradio theming guide and borrowed from https://huggingface.co/spaces/shivi/dolly-v2-demo
class SeafoamCustom(Base):
def __init__(
self,
*,
primary_hue: colors.Color | str = colors.emerald,
secondary_hue: colors.Color | str = colors.blue,
neutral_hue: colors.Color | str = colors.blue,
spacing_size: sizes.Size | str = sizes.spacing_md,
radius_size: sizes.Size | str = sizes.radius_md,
font: fonts.Font
| str
| Iterable[fonts.Font | str] = (
fonts.GoogleFont("Quicksand"),
"ui-sans-serif",
"sans-serif",
),
font_mono: fonts.Font
| str
| Iterable[fonts.Font | str] = (
fonts.GoogleFont("IBM Plex Mono"),
"ui-monospace",
"monospace",
),
):
super().__init__(
primary_hue=primary_hue,
secondary_hue=secondary_hue,
neutral_hue=neutral_hue,
spacing_size=spacing_size,
radius_size=radius_size,
font=font,
font_mono=font_mono,
)
super().set(
button_primary_background_fill="linear-gradient(90deg, *primary_300, *secondary_400)",
button_primary_background_fill_hover="linear-gradient(90deg, *primary_200, *secondary_300)",
button_primary_text_color="white",
button_primary_background_fill_dark="linear-gradient(90deg, *primary_600, *secondary_800)",
block_shadow="*shadow_drop_lg",
button_shadow="*shadow_drop_lg",
input_background_fill="zinc",
input_border_color="*secondary_300",
input_shadow="*shadow_drop",
input_shadow_focus="*shadow_drop_lg",
)
seafoam = SeafoamCustom()
with gr.Blocks(theme=seafoam, analytics_enabled=False, css=css) as demo:
with gr.Column():
gr.Markdown(
""" ## Mistral-7b
Type in the box below and click the button to generate answers to your most pressing questions!
"""
)
with gr.Row():
with gr.Column(scale=3):
instruction = gr.Textbox(placeholder="Enter your question here", label="Question", elem_id="q-input")
with gr.Box():
gr.Markdown("**Answer**")
output = gr.Markdown(elem_id="q-output")
submit = gr.Button("Generate", variant="primary")
gr.Examples(
examples=examples,
inputs=[instruction],
cache_examples=True,
fn=process_example,
outputs=[output],
)
submit.click(generate, inputs=[instruction], outputs=[output])
instruction.submit(generate, inputs=[instruction], outputs=[output])
demo.queue(concurrency_count=1).launch(debug=False) |