add model
Browse files- config.json +66 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/content/drive/MyDrive/ColabModels/MBERT_MASKING_THESEUS/pytorch_model/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"by_layer_is_trainable": {
|
| 8 |
+
"0": true,
|
| 9 |
+
"1": true,
|
| 10 |
+
"10": true,
|
| 11 |
+
"11": true,
|
| 12 |
+
"12": true,
|
| 13 |
+
"13": true,
|
| 14 |
+
"14": true,
|
| 15 |
+
"15": true,
|
| 16 |
+
"16": true,
|
| 17 |
+
"17": true,
|
| 18 |
+
"18": true,
|
| 19 |
+
"19": true,
|
| 20 |
+
"2": true,
|
| 21 |
+
"20": true,
|
| 22 |
+
"21": true,
|
| 23 |
+
"22": true,
|
| 24 |
+
"23": true,
|
| 25 |
+
"3": true,
|
| 26 |
+
"4": true,
|
| 27 |
+
"5": true,
|
| 28 |
+
"6": true,
|
| 29 |
+
"7": true,
|
| 30 |
+
"8": true,
|
| 31 |
+
"9": true
|
| 32 |
+
},
|
| 33 |
+
"classifier_dropout": null,
|
| 34 |
+
"cls_trainable": true,
|
| 35 |
+
"directionality": "bidi",
|
| 36 |
+
"embedding_postprocessor_trainable": true,
|
| 37 |
+
"embeddings_layer_norm_trainable": true,
|
| 38 |
+
"hidden_act": "gelu",
|
| 39 |
+
"hidden_dropout_prob": 0.1,
|
| 40 |
+
"hidden_size": 768,
|
| 41 |
+
"init_optimizer_variables": true,
|
| 42 |
+
"initializer_range": 0.02,
|
| 43 |
+
"intermediate_size": 3072,
|
| 44 |
+
"layer_norm_eps": 1e-12,
|
| 45 |
+
"max_position_embeddings": 512,
|
| 46 |
+
"model_type": "bert",
|
| 47 |
+
"num_attention_heads": 12,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 0,
|
| 50 |
+
"pooler_fc_size": 768,
|
| 51 |
+
"pooler_num_attention_heads": 12,
|
| 52 |
+
"pooler_num_fc_layers": 3,
|
| 53 |
+
"pooler_size_per_head": 128,
|
| 54 |
+
"pooler_trainable": true,
|
| 55 |
+
"pooler_type": "first_token_transform",
|
| 56 |
+
"position_embedding_type": "absolute",
|
| 57 |
+
"position_embeddings_trainable": true,
|
| 58 |
+
"token_type_trainable": true,
|
| 59 |
+
"torch_dtype": "float32",
|
| 60 |
+
"transformer_trainable": true,
|
| 61 |
+
"transformers_version": "4.18.0",
|
| 62 |
+
"type_vocab_size": 2,
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"vocab_size": 119547,
|
| 65 |
+
"word_embeddings_trainable": true
|
| 66 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:988666ad7d905e205fe83f3e228e5e05308ed0d611d8d118370950268f62e712
|
| 3 |
+
size 541826859
|