init
Browse files- config.json +46 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "klue/roberta-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "fragment",
|
| 16 |
+
"1": "statement",
|
| 17 |
+
"2": "question",
|
| 18 |
+
"3": "command",
|
| 19 |
+
"4": "rhetorical question",
|
| 20 |
+
"5": "rhetorical command",
|
| 21 |
+
"6": "intonation-depedent utterance"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"command": 3,
|
| 27 |
+
"fragment": 0,
|
| 28 |
+
"intonation-depedent utterance": 6,
|
| 29 |
+
"question": 2,
|
| 30 |
+
"rhetorical command": 5,
|
| 31 |
+
"rhetorical question": 4,
|
| 32 |
+
"statement": 1
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-05,
|
| 35 |
+
"max_position_embeddings": 514,
|
| 36 |
+
"model_type": "roberta",
|
| 37 |
+
"num_attention_heads": 12,
|
| 38 |
+
"num_hidden_layers": 6,
|
| 39 |
+
"pad_token_id": 1,
|
| 40 |
+
"position_embedding_type": "absolute",
|
| 41 |
+
"tokenizer_class": "BertTokenizer",
|
| 42 |
+
"transformers_version": "4.11.3",
|
| 43 |
+
"type_vocab_size": 1,
|
| 44 |
+
"use_cache": true,
|
| 45 |
+
"vocab_size": 32000
|
| 46 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e56a64376750165a98d5f370632e7c329bb5169e7604b810c5fbf729ad764a0
|
| 3 |
+
size 272534680
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "bos_token": "[CLS]", "eos_token": "[SEP]", "add_prefix_space": false, "errors": "replace", "sep_token": "[SEP]", "cls_token": "[CLS]", "pad_token": "[PAD]", "mask_token": "[MASK]", "do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": "/home/jupyter/.cache/huggingface/transformers/9ce71a5afff600bb47488785ec31125c4a485302e21d660291b10925f8bfcb67.70c17d6e4d492c8f24f5bb97ab56c7f272e947112c6faf9dd846da42ba13eb23", "name_or_path": "klue/roberta-small", "tokenizer_class": "RobertaTokenizer"}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|