albert-small-kor-v1 모델 업로드
Browse files- config.json +28 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +25 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"AlbertForPreTraining"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0,
|
| 6 |
+
"bos_token_id": 2,
|
| 7 |
+
"classifier_dropout_prob": 0.1,
|
| 8 |
+
"embedding_size": 128,
|
| 9 |
+
"eos_token_id": 3,
|
| 10 |
+
"hidden_act": "gelu_new",
|
| 11 |
+
"hidden_dropout_prob": 0,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"inner_group_num": 1,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-12,
|
| 17 |
+
"max_position_embeddings": 512,
|
| 18 |
+
"model_type": "albert",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_groups": 1,
|
| 21 |
+
"num_hidden_layers": 6,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.21.2",
|
| 26 |
+
"type_vocab_size": 2,
|
| 27 |
+
"vocab_size": 30000
|
| 28 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8469a5c0058d2296d422b6022afc62d2b29a15f788914d6e907e62a6abf1a17
|
| 3 |
+
size 47270018
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "[MASK]",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "[PAD]",
|
| 13 |
+
"sep_token": "[SEP]",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acfb0d032fb54ca202c9e07d98ef2bf4566d39de774d0e65dba3b9562a9afac0
|
| 3 |
+
size 773715
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"eos_token": "[SEP]",
|
| 6 |
+
"keep_acccents": false,
|
| 7 |
+
"keep_accents": true,
|
| 8 |
+
"mask_token": {
|
| 9 |
+
"__type": "AddedToken",
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"max_len": 128,
|
| 17 |
+
"name_or_path": "../../data11/ai_hub/vocab/tl1-1줄-mecab-30000-sp-unigram-22M-vocab",
|
| 18 |
+
"pad_token": "[PAD]",
|
| 19 |
+
"remove_space": true,
|
| 20 |
+
"sep_token": "[SEP]",
|
| 21 |
+
"sp_model_kwargs": {},
|
| 22 |
+
"special_tokens_map_file": "../../data11/ai_hub/vocab/tl1-1줄-mecab-30000-sp-unigram-22M-vocab/special_tokens_map.json",
|
| 23 |
+
"tokenizer_class": "AlbertTokenizer",
|
| 24 |
+
"unk_token": "[UNK]"
|
| 25 |
+
}
|