Model: teven/cross_all_bs192_hardneg_finetuned_WebNLG2020_relevance Source: Original Platform
31 lines
737 B
JSON
31 lines
737 B
JSON
{
|
|
"_name_or_path": "hyperparam_search/2020_relevance/cross_all_bs192_hardneg/lr2e-05_bs32/best_model",
|
|
"architectures": [
|
|
"MPNetModel"
|
|
],
|
|
"attention_probs_dropout_prob": 0.1,
|
|
"bos_token_id": 0,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "gelu",
|
|
"hidden_dropout_prob": 0.1,
|
|
"hidden_size": 768,
|
|
"id2label": {
|
|
"0": "LABEL_0"
|
|
},
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 3072,
|
|
"label2id": {
|
|
"LABEL_0": 0
|
|
},
|
|
"layer_norm_eps": 1e-05,
|
|
"max_position_embeddings": 514,
|
|
"model_type": "mpnet",
|
|
"num_attention_heads": 12,
|
|
"num_hidden_layers": 12,
|
|
"pad_token_id": 1,
|
|
"relative_attention_num_buckets": 32,
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.21.0.dev0",
|
|
"vocab_size": 30531
|
|
}
|