Spaces:
Running
Running
| import gradio as gr | |
| import os | |
| import torch | |
| import numpy as np | |
| from transformers import AutoModelForSequenceClassification | |
| from transformers import AutoTokenizer | |
| from huggingface_hub import HfApi | |
| HF_TOKEN = os.environ["hf_read"] | |
| languages = [ | |
| "English" | |
| ] | |
| from label_dicts import ONTOLISST_LABEL_NAMES | |
| # --- DEBUG --- | |
| import shutil | |
| def convert_size(size): | |
| for unit in ['B', 'KB', 'MB', 'GB', 'TB', 'PB']: | |
| if size < 1024: | |
| return f"{size:.2f} {unit}" | |
| size /= 1024 | |
| def get_disk_space(path="/"): | |
| total, used, free = shutil.disk_usage(path) | |
| return { | |
| "Total": convert_size(total), | |
| "Used": convert_size(used), | |
| "Free": convert_size(free) | |
| } | |
| # --- | |
| def build_huggingface_path(language: str): | |
| return "poltextlab/xlm-roberta-large_ontolisst_v1" | |
| def predict(text, model_id, tokenizer_id): | |
| device = torch.device("cpu") | |
| model = AutoModelForSequenceClassification.from_pretrained(model_id, low_cpu_mem_usage=True, device_map="auto", offload_folder="offload", token=HF_TOKEN) | |
| tokenizer = AutoTokenizer.from_pretrained(tokenizer_id) | |
| # --- DEBUG --- | |
| disk_space = get_disk_space('/data/') | |
| print("Disk Space Info:") | |
| for key, value in disk_space.items(): | |
| print(f"{key}: {value}") | |
| # --- | |
| model.to(device) | |
| inputs = tokenizer(text, | |
| max_length=256, | |
| truncation=True, | |
| padding="do_not_pad", | |
| return_tensors="pt").to(device) | |
| model.eval() | |
| with torch.no_grad(): | |
| logits = model(**inputs).logits | |
| probs = torch.nn.functional.softmax(logits, dim=1).cpu().numpy().flatten() | |
| predicted_class_id = probs.argmax() | |
| predicted_class_id = {4: 2, 5: 1}.get(predicted_class_id, 0) | |
| output_pred = ONTOLISST_LABEL_NAMES.get(predicted_class_id, predicted_class_id) | |
| output_info = f'<p style="text-align: center; display: block">Prediction was made using the <a href="https://huggingface.co/{model_id}">{model_id}</a> model.</p>' | |
| return output_pred, output_info | |
| def predict_cap(text, language): | |
| model_id = build_huggingface_path(language) | |
| tokenizer_id = "xlm-roberta-large" | |
| return predict(text, model_id, tokenizer_id) | |
| demo = gr.Interface( | |
| title="ONTOLISST Babel Demo", | |
| fn=predict_cap, | |
| inputs=[gr.Textbox(lines=6, label="Input"), | |
| gr.Dropdown(languages, label="Language")], | |
| outputs=[gr.Label(num_top_classes=3, label="Output"), gr.Markdown()]) | |