File size: 5,972 Bytes
3928a9f
 
3fb614b
b0d15d2
 
8eefb9c
d6d59d4
8eefb9c
42435e1
3fb614b
 
 
 
 
 
 
 
 
c9152b5
d6d59d4
 
 
8eefb9c
c9152b5
d2758fe
c9152b5
8eefb9c
3fb614b
8eefb9c
d75f5ef
 
 
ed9ce62
6e8442c
3fb614b
 
 
d75f5ef
 
 
3fb614b
 
 
 
 
 
d75f5ef
7bd3786
3fb614b
8343a97
952a2cb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3fb614b
 
ed9ce62
8343a97
1424ecd
3fb614b
 
 
 
 
43cbeb6
 
3fb614b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8343a97
3fb614b
 
 
 
 
 
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
from __future__ import annotations
from typing import Iterable
import gradio as gr
from gradio.themes.base import Base
from gradio.themes.utils import colors, fonts, sizes
from instruct_pipeline import InstructionTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, BitsAndBytesConfig

import torch

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"],
)

tokenizer = AutoTokenizer.from_pretrained("databricks/dolly-v2-12b", padding_side="left")
quantization_config = BitsAndBytesConfig(load_in_8bit=True,
                                         llm_int8_threshold=200.0)
model = AutoModelForCausalLM.from_pretrained("databricks/dolly-v2-12b", device_map="auto", quantization_config=quantization_config)

generate_text = InstructionTextGenerationPipeline(model=model, tokenizer=tokenizer)

#generate_text = pipeline(model="databricks/dolly-v2-12b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")

def generate(instruction): 
    response = generate_text(instruction)
    result = ""
    for word in response.split(" "):
        result += word + " "
        yield result
        
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?",
    "Write me a tweet about the release of Dolly 2.0, a new LLM",
    "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(
            """ ## Dolly 2.0
            
            Dolly 2.0 is a 12B parameter language model based on the EleutherAI pythia model family and fine-tuned exclusively on a new, high-quality human generated instruction following dataset, crowdsourced among Databricks employees. For more details, please refer to the [model card](https://huggingface.co./databricks/dolly-v2-12b)
            
            Type in the box below and click the button to generate answers to your most pressing questions!
            
      """
        )
        gr.HTML("<p>You can duplicate this Space to run it privately without a queue for shorter queue times  : <a style='display:inline-block' href='https://huggingface.co./spaces/RamAnanth1/Dolly-v2?duplicate=true'><img src='https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14' alt='Duplicate Space'></a> </p>")

        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=False,
                    fn=process_example,
                    outputs=[output],
                )
        


    submit.click(generate, inputs=[instruction], outputs=[output])
    instruction.submit(generate, inputs=[instruction], outputs=[output])

demo.queue(concurrency_count=16).launch(debug=True)