|
{ |
|
"_name_or_path": "MoritzLaurer/ModernBERT-large-zeroshot-v2.0", |
|
"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": 1024, |
|
"id2label": { |
|
"0": "AI Applications", |
|
"1": "AI Infrastructure", |
|
"10": "Deep Learning", |
|
"11": "Embeddings", |
|
"12": "Ethics", |
|
"13": "Evaluation", |
|
"14": "Fine-Tuning", |
|
"15": "Gaming", |
|
"16": "Generative AI", |
|
"17": "Gradio", |
|
"18": "Hardware", |
|
"19": "Hugging Face", |
|
"2": "Agents", |
|
"20": "Image", |
|
"21": "LLMs", |
|
"22": "ML Theory", |
|
"23": "MLOps", |
|
"24": "Model Optimization", |
|
"25": "Multimodal", |
|
"26": "NLP", |
|
"27": "Reinforcement Learning", |
|
"28": "Research Papers", |
|
"29": "Robotics", |
|
"3": "Argilla", |
|
"30": "Security", |
|
"31": "Time Series", |
|
"32": "Tutorials", |
|
"33": "Video", |
|
"34": "XetHub", |
|
"4": "Audio", |
|
"5": "Cloud Deployment", |
|
"6": "Code", |
|
"7": "Computer Vision", |
|
"8": "Data Engineering", |
|
"9": "Data Science" |
|
}, |
|
"initializer_cutoff_factor": 2.0, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 2624, |
|
"label2id": { |
|
"AI Applications": "0", |
|
"AI Infrastructure": "1", |
|
"Agents": "2", |
|
"Argilla": "3", |
|
"Audio": "4", |
|
"Cloud Deployment": "5", |
|
"Code": "6", |
|
"Computer Vision": "7", |
|
"Data Engineering": "8", |
|
"Data Science": "9", |
|
"Deep Learning": "10", |
|
"Embeddings": "11", |
|
"Ethics": "12", |
|
"Evaluation": "13", |
|
"Fine-Tuning": "14", |
|
"Gaming": "15", |
|
"Generative AI": "16", |
|
"Gradio": "17", |
|
"Hardware": "18", |
|
"Hugging Face": "19", |
|
"Image": "20", |
|
"LLMs": "21", |
|
"ML Theory": "22", |
|
"MLOps": "23", |
|
"Model Optimization": "24", |
|
"Multimodal": "25", |
|
"NLP": "26", |
|
"Reinforcement Learning": "27", |
|
"Research Papers": "28", |
|
"Robotics": "29", |
|
"Security": "30", |
|
"Time Series": "31", |
|
"Tutorials": "32", |
|
"Video": "33", |
|
"XetHub": "34" |
|
}, |
|
"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": 16, |
|
"num_hidden_layers": 28, |
|
"pad_token_id": 50283, |
|
"position_embedding_type": "absolute", |
|
"problem_type": "multi_label_classification", |
|
"reference_compile": true, |
|
"sep_token_id": 50282, |
|
"sparse_pred_ignore_index": -100, |
|
"sparse_prediction": false, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.48.0.dev0", |
|
"vocab_size": 50368 |
|
} |
|
|