Text Classification
Transformers
ONNX
Safetensors
Transformers.js
modernbert
topic-classification
domain-classification
web-classification
weborganizer
data-curation
pretraining-data
mmbert
text-embeddings-inference
Instructions to use Horizon-Labs/multilingual-web-topic-format-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Horizon-Labs/multilingual-web-topic-format-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Horizon-Labs/multilingual-web-topic-format-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Horizon-Labs/multilingual-web-topic-format-base") model = AutoModelForSequenceClassification.from_pretrained("Horizon-Labs/multilingual-web-topic-format-base", device_map="auto") - Transformers.js
How to use Horizon-Labs/multilingual-web-topic-format-base with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-classification', 'Horizon-Labs/multilingual-web-topic-format-base'); - Notebooks
- Google Colab
- Kaggle
Download training/train_log.json from Horizon-Labs/multilingual-web-topic-format-base: direct link, hf CLI and curl.
- Browser
- Download file 1.92 kB
-
https://huggingface.co/Horizon-Labs/multilingual-web-topic-format-base/resolve/main/training/train_log.json
- Command line
-
hf download hf://Horizon-Labs/multilingual-web-topic-format-base/training/train_log.json
-
curl -L -o train_log.json https://huggingface.co/Horizon-Labs/multilingual-web-topic-format-base/resolve/main/training/train_log.json
1.92 kB
| { | |
| "args": { | |
| "base": "jhu-clsp/mmBERT-base", | |
| "data": "see code/", | |
| "out": "model", | |
| "max_len": 512, | |
| "pos_weight": 1.0, | |
| "tokens_per_batch": 32768, | |
| "lr": 5e-05, | |
| "epochs": 3, | |
| "warmup": 0.06, | |
| "wd": 0.01, | |
| "seed": 1, | |
| "eval_every": 1000, | |
| "labels": "topic_adult_content,topic_art_design,topic_software_development,topic_crime_law,topic_education_jobs,topic_electronics_hardware,topic_entertainment,topic_social_life,topic_fashion_beauty,topic_finance_business,topic_food_dining,topic_games,topic_health,topic_history_geography,topic_home_hobbies,topic_industrial,topic_literature,topic_politics,topic_religion,topic_science_math_technology,topic_software,topic_sports_fitness,topic_transportation,topic_travel_tourism,format_academic_writing,format_content_listing,format_creative_writing,format_customer_support_page,format_discussion_forum_comment_section,format_faqs,format_incomplete_content,format_knowledge_article,format_legal_notices,format_listicle,format_news_article,format_nonfiction_writing,format_organizational_about_page,format_organizational_announcement,format_personal_about_page,format_personal_blog,format_product_page,format_q_a_forum,format_spam_ads,format_structured_data,format_technical_writing,format_transcript_interview,format_tutorial_how_to_guide,format_user_reviews", | |
| "regression": false, | |
| "context": false | |
| }, | |
| "log": [ | |
| { | |
| "step": 1000, | |
| "macro_f1": 0.9871291835636151, | |
| "bce": 0.052475491213249965 | |
| }, | |
| { | |
| "step": 2000, | |
| "macro_f1": 0.9896427882307777, | |
| "bce": 0.049017800571935936 | |
| }, | |
| { | |
| "step": 3000, | |
| "macro_f1": 0.9912372172173942, | |
| "bce": 0.04638443514136261 | |
| }, | |
| { | |
| "step": 4000, | |
| "macro_f1": 0.9915471886292259, | |
| "bce": 0.04578748467761121 | |
| }, | |
| { | |
| "step": 5000, | |
| "macro_f1": 0.9918407740583784, | |
| "bce": 0.045128118377375084 | |
| }, | |
| { | |
| "step": 5619, | |
| "macro_f1": 0.9919088847966561, | |
| "bce": 0.04503493070270418 | |
| } | |
| ] | |
| } |