Text Classification
Transformers
TensorBoard
Safetensors
modernbert
wissamantoun's picture
Upload folder using huggingface_hub
9adb430 verified
{
"architectures": [
"ModernBertForSequenceClassification"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 50281,
"classifier_activation": "gelu",
"classifier_bias": false,
"classifier_dropout": 0.0,
"classifier_pooling": "mean",
"cls_token_id": 50281,
"decoder_bias": true,
"deterministic_flash_attn": false,
"embedding_dropout": 0.0,
"eos_token_id": 50282,
"global_attn_every_n_layers": 3,
"global_rope_theta": 160000.0,
"gradient_checkpointing": false,
"hidden_activation": "gelu",
"hidden_size": 768,
"num_labels": 24,
"id2label": {
"0": "Academic Writing",
"1": "Content Listing",
"10": "News Article",
"11": "Nonfiction Writing",
"12": "About (Org.)",
"13": "News (Org.)",
"14": "About (Pers.)",
"15": "Personal Blog",
"16": "Product Page",
"17": "Q&A Forum",
"18": "Spam / Ads",
"19": "Structured Data",
"2": "Creative Writing",
"20": "Documentation",
"21": "Audio Transcript",
"22": "Tutorial",
"23": "User Review",
"3": "Customer Support",
"4": "Comment Section",
"5": "FAQ",
"6": "Truncated",
"7": "Knowledge Article",
"8": "Legal Notices",
"9": "Listicle"
},
"initializer_cutoff_factor": 2.0,
"initializer_range": 0.02,
"intermediate_size": 1152,
"label2id": {
"About (Org.)": 12,
"About (Pers.)": 14,
"Academic Writing": 0,
"Audio Transcript": 21,
"Comment Section": 4,
"Content Listing": 1,
"Creative Writing": 2,
"Customer Support": 3,
"Documentation": 20,
"FAQ": 5,
"Knowledge Article": 7,
"Legal Notices": 8,
"Listicle": 9,
"News (Org.)": 13,
"News Article": 10,
"Nonfiction Writing": 11,
"Personal Blog": 15,
"Product Page": 16,
"Q&A Forum": 17,
"Spam / Ads": 18,
"Structured Data": 19,
"Truncated": 6,
"Tutorial": 22,
"User Review": 23
},
"layer_norm_eps": 1e-05,
"local_attention": 128,
"local_rope_theta": 10000.0,
"max_position_embeddings": 8192,
"mlp_bias": false,
"mlp_dropout": 0.0,
"model_type": "modernbert",
"norm_bias": false,
"norm_eps": 1e-05,
"num_attention_heads": 12,
"num_hidden_layers": 22,
"pad_token_id": 50283,
"position_embedding_type": "absolute",
"reference_compile": true,
"repad_logits_with_grad": false,
"sep_token_id": 50282,
"sparse_pred_ignore_index": -100,
"sparse_prediction": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"vocab_size": 50368
}