Spaces:
Sleeping
Sleeping
| 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) |