File size: 1,286 Bytes
208c7af |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
{
"_name_or_path": "./models/longformer-finetuned",
"architectures": [
"LongformerForSequenceClassification"
],
"attention_mode": "longformer",
"attention_probs_dropout_prob": 0.1,
"attention_window": [
4096,
4096,
4096,
4096,
4096,
4096,
4096,
4096,
4096,
4096,
4096,
4096
],
"bos_token_id": 0,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "anachronistically_relevant",
"1": "creativity",
"2": "grammar_coherence",
"3": "overall_quality",
"4": "relevance",
"5": "style_consistency"
},
"ignore_attention_mask": false,
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"anachronistically_relevant": 0,
"creativity": 1,
"grammar_coherence": 2,
"overall_quality": 3,
"relevance": 4,
"style_consistency": 5
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 4098,
"model_type": "longformer",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"onnx_export": false,
"pad_token_id": 1,
"sep_token_id": 2,
"torch_dtype": "float32",
"transformers_version": "4.44.2",
"type_vocab_size": 1,
"vocab_size": 50265
}
|