Upload BertForMaskedLM
Browse files- config.json +39 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "hf_bert/bp_medium_step49",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"attn_norm_layer_type": "layer_norm",
|
| 8 |
+
"attn_num_groups": "None",
|
| 9 |
+
"classifier_dropout": "None",
|
| 10 |
+
"embedding_norm_layer_type": "layer_norm",
|
| 11 |
+
"embedding_num_groups": "None",
|
| 12 |
+
"embedding_size": 768,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0.1,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"layer_norm_eps": 1e-12,
|
| 19 |
+
"max_position_embeddings": 2000,
|
| 20 |
+
"model_type": "bert",
|
| 21 |
+
"mup": false,
|
| 22 |
+
"num_attention_heads": 16,
|
| 23 |
+
"num_hidden_layers": 24,
|
| 24 |
+
"output_mult": 1,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"prenorm": false,
|
| 28 |
+
"query_zero_init": false,
|
| 29 |
+
"readout_zero_init": false,
|
| 30 |
+
"summary_activation": "gelu",
|
| 31 |
+
"summary_last_dropout": 0.1,
|
| 32 |
+
"summary_type": "first",
|
| 33 |
+
"summary_use_proj": true,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.25.1",
|
| 36 |
+
"type_vocab_size": 2,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 9
|
| 39 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89804ea939a065d68ca73e7ce65ec10e74bc97db3bf65b019e9223be1bd7e99c
|
| 3 |
+
size 689134009
|