Upload BertForMaskedLM
Browse files- config.json +46 -0
- generation_config.json +5 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "5CD-AI/twhin-bert-large-viso-20kvocab-uit-10epochs",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4096,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "relative_key",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.38.2",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 20002,
|
| 25 |
+
"vocabtrimmer": {
|
| 26 |
+
"mining_config": {
|
| 27 |
+
"dataset": "vocabtrimmer/mc4_validation",
|
| 28 |
+
"dataset_column": "text",
|
| 29 |
+
"dataset_name": "en",
|
| 30 |
+
"dataset_split": "validation",
|
| 31 |
+
"language": "en",
|
| 32 |
+
"min_frequency": 2,
|
| 33 |
+
"target_vocab_size": 20000
|
| 34 |
+
},
|
| 35 |
+
"stats": {
|
| 36 |
+
"compression_rate_embedding": 8.000735994112047,
|
| 37 |
+
"compression_rate_full": 58.03015244164301,
|
| 38 |
+
"parameter_size_embedding/raw": 256002048,
|
| 39 |
+
"parameter_size_embedding/trimmed": 20482048,
|
| 40 |
+
"parameter_size_full/raw": 561712786,
|
| 41 |
+
"parameter_size_full/trimmed": 325962786,
|
| 42 |
+
"vocab_size/raw": 250002,
|
| 43 |
+
"vocab_size/trimmed": 20002
|
| 44 |
+
}
|
| 45 |
+
}
|
| 46 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"pad_token_id": 0,
|
| 4 |
+
"transformers_version": "4.38.2"
|
| 5 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67ed1eeeb80dd55ee8496d498eac9a4206954dc2dda64670d8273ab59e646d61
|
| 3 |
+
size 1303901552
|