app.py

import os
import json
from datetime import datetime, timezone
from dataclasses import dataclass
from datasets import load_dataset, Dataset
import pandas as pd
import gradio as gr
from huggingface_hub import HfApi, snapshot_download
from huggingface_hub.hf_api import ModelInfo
from enum import Enum


OWNER = "EnergyStarAI"
COMPUTE_SPACE = f"{OWNER}/launch-computation-example"


TOKEN = os.environ.get("DEBUG")
API = HfApi(token=TOKEN)

requests= load_dataset("EnergyStarAI/requests_debug", split="test", token=TOKEN)

tasks = ['ASR', 'Object Detection', 'Text Classification', 'Image Captioning', 'Question Answering', 'Text Generation', 'Image Classification',
        'Sentence Similarity', 'Image Generation', 'Summarization']


##### Data classes need for the leaderboard Submit Model menu. #####
@dataclass
class ModelDetails:
    name: str
    display_name: str = ""
    symbol: str = "" # emoji

class WeightType(Enum):
    Adapter = ModelDetails("Adapter")
    Original = ModelDetails("Original")
    Delta = ModelDetails("Delta")

            
class ModelType(Enum):
    PT = ModelDetails(name="pretrained", symbol="🟢")
    FT = ModelDetails(name="fine-tuned", symbol="🔶")
    IFT = ModelDetails(name="instruction-tuned", symbol="⭕")
    RL = ModelDetails(name="RL-tuned", symbol="🟦")
    Unknown = ModelDetails(name="", symbol="?")

    def to_str(self, separator=" "):
        return f"{self.value.symbol}{separator}{self.value.name}"

    @staticmethod
    def from_str(type):
        if "fine-tuned" in type or "🔶" in type:
            return ModelType.FT
        if "pretrained" in type or "🟢" in type:
            return ModelType.PT
        if "RL-tuned" in type or "🟦" in type:
            return ModelType.RL
        if "instruction-tuned" in type or "⭕" in type:
            return ModelType.IFT
        return ModelType.Unknown

##### End of classes required by the leaderboard Submit Model menu #####



def start_compute_space():
    API.restart_space(COMPUTE_SPACE)  
    return f"Okay! {COMPUTE_SPACE} should be running now!"


def get_model_size(model_info: ModelInfo):
    """Gets the model size from the configuration, or the model name if the configuration does not contain the information."""
    try:
        model_size = round(model_info.safetensors["total"] / 1e9, 3)
    except (AttributeError, TypeError):
        return 0  # Unknown model sizes are indicated as 0, see NUMERIC_INTERVALS in app.py
    return model_size


def add_new_eval(
    repo_id: str,
    task: str,
):
    model_owner = repo_id.split("/")[0]
    model_name = repo_id.split("/")[1]  
    
    current_time = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")

    # Is the model info correctly filled?
    try:
        model_info = API.model_info(repo_id=repo_id)
    except Exception:
        print("Could not find information for model %s" % (model))
        return
    #    return styled_error("Could not get your model information. Please fill it up properly.")

    model_size = get_model_size(model_info=model_info)
    
    print("Adding request")

    requests_dset = requests.to_pandas()
    
    request_dict = {
        "model": repo_id,
        "precision": "N/A",
        "status": "PENDING",
        "submitted_time": pd.to_datetime(current_time),
        "task": task,
        "likes": model_info.likes,
        "params": model_size}
        #"license": license,
        #"private": False,
    #}

    print("Writing out request file to dataset")
    df_request_dict = pd.DataFrame([request_dict])
    print(df_request_dict)
    df_final = pd.concat([requests_dset, df_request_dict], ignore_index=True)
    updated_dset =Dataset.from_pandas(df_final)
    updated_dset.push_to_hub("EnergyStarAI/requests_debug", split="test", token=TOKEN)
    
    print("Starting compute space at %s " % COMPUTE_SPACE)
    return start_compute_space()

def print_existing_models():
    requests = load_dataset("EnergyStarAI/requests_debug", split="test")
    requests_dset = requests.to_pandas()
    model_list= requests_dset[requests_dset['status'] == 'COMPLETED']
    return model_list        

with gr.Blocks() as demo:
    gr.Markdown("# Energy Star Submission Portal - v.0 (2024) 🌎 💻 🌟")
    gr.Markdown("## ✉️✨ Submit your model here!", elem_classes="markdown-text")
    gr.Markdown("## Fill out below then click **Run Analysis** to create the request file and launch the job.")
    gr.Markdown("## The [Project Leaderboard](https://huggingface.co/spaces/EnergyStarAI/2024_Leaderboard) will be updated quarterly, as new models get submitted.")
    with gr.Row():
        with gr.Column():
            task = gr.Dropdown(
                choices=tasks,
                label="Choose a benchmark task",
                value = 'Text Generation',
                multiselect=False,
                interactive=True,
            )
        with gr.Column():
            model_name_textbox = gr.Textbox(label="Model name")

    with gr.Row():
        with gr.Column():
            submit_button = gr.Button("Run Analysis")
            submission_result = gr.Markdown()
            submit_button.click(
                fn=add_new_eval,
                inputs=[
                    model_name_textbox,
                    task,
                ],
                outputs=submission_result,
            )
    with gr.Row():
        gr.Dataframe(print_existing_models())
demo.launch()