File size: 1,238 Bytes
b78d159 |
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 |
{
"_name_or_path": "jinaai/jina-bert-flash-implementation",
"auto_map": {
"AutoConfig": "jinaai/jina-bert-flash-implementation--configuration_bert.JinaBertConfig",
"AutoModel": "jinaai/jina-bert-flash-implementation--modeling_bert.BertModel",
"AutoModelForPreTraining": "jinaai/jina-bert-flash-implementation--modeling_bert.BertForPreTraining",
"AutoModelForMaskedLM": "jinaai/jina-bert-flash-implementation--modeling_bert.BertForPreTraining"
},
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"dense_seq_output": false,
"emb_pooler": null,
"fused_bias_fc": false,
"fused_dropout_add_ln": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"last_layer_subset": false,
"layer_norm_eps": 1e-12,
"mlp_checkpoint_lvl": 0,
"mlp_type": "glu",
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"num_loras": 5,
"pad_token_id": 0,
"pad_vocab_size_multiple": 1,
"torch_dtype": "float16",
"transformers_version": "4.39.3",
"type_vocab_size": 2,
"use_flash_attn": true,
"use_qk_norm": false,
"vocab_size": 30528,
"window_size": [
-1,
-1
]
}
|