import gradio as gr from transformers import pipeline 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"], ) instruct_pipeline = pipeline(model="databricks/dolly-v2-12b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto") def generate(instruction): response = instruct_pipeline(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" ] def process_example(args): for x in generate(args): pass return x css = ".generating {visibility: hidden}" with gr.Blocks(theme=theme, analytics_enabled=False, css=css) as demo: with gr.Column(): gr.Markdown( """ ## Dolly 2.0: World's First Truly Open Instruction-Tuned LLM 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("
You can duplicate this Space to run it privately without a queue for shorter queue times :
") 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)