Initial commit
Browse files- added_tokens.json +3 -0
- bpe.codes +0 -0
- config.json +60 -0
- intent_encoder.pkl +3 -0
- pytorch_model.bin +3 -0
- slot_labels.json +15 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +12 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 64000
|
| 3 |
+
}
|
bpe.codes
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "vinai/phobert-base",
|
| 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": "LABEL_0",
|
| 16 |
+
"1": "LABEL_1",
|
| 17 |
+
"2": "LABEL_2",
|
| 18 |
+
"3": "LABEL_3",
|
| 19 |
+
"4": "LABEL_4",
|
| 20 |
+
"5": "LABEL_5",
|
| 21 |
+
"6": "LABEL_6",
|
| 22 |
+
"7": "LABEL_7",
|
| 23 |
+
"8": "LABEL_8",
|
| 24 |
+
"9": "LABEL_9",
|
| 25 |
+
"10": "LABEL_10",
|
| 26 |
+
"11": "LABEL_11",
|
| 27 |
+
"12": "LABEL_12"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"LABEL_0": 0,
|
| 33 |
+
"LABEL_1": 1,
|
| 34 |
+
"LABEL_10": 10,
|
| 35 |
+
"LABEL_11": 11,
|
| 36 |
+
"LABEL_12": 12,
|
| 37 |
+
"LABEL_2": 2,
|
| 38 |
+
"LABEL_3": 3,
|
| 39 |
+
"LABEL_4": 4,
|
| 40 |
+
"LABEL_5": 5,
|
| 41 |
+
"LABEL_6": 6,
|
| 42 |
+
"LABEL_7": 7,
|
| 43 |
+
"LABEL_8": 8,
|
| 44 |
+
"LABEL_9": 9
|
| 45 |
+
},
|
| 46 |
+
"layer_norm_eps": 1e-05,
|
| 47 |
+
"max_position_embeddings": 258,
|
| 48 |
+
"model_type": "roberta",
|
| 49 |
+
"num_attention_heads": 12,
|
| 50 |
+
"num_hidden_layers": 12,
|
| 51 |
+
"pad_token_id": 1,
|
| 52 |
+
"position_embedding_type": "absolute",
|
| 53 |
+
"problem_type": "single_label_classification",
|
| 54 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.30.0",
|
| 57 |
+
"type_vocab_size": 1,
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 64001
|
| 60 |
+
}
|
intent_encoder.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:452b5c57c4c5f9640da33146e0a6f28b9d70a807056bfbe822a1db3058ce12e7
|
| 3 |
+
size 1695
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9dcf33ceba3444648e58b5fa8d72360612f2751411f5a67bdeba0c8c9c9b99b
|
| 3 |
+
size 540104882
|
slot_labels.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
"O",
|
| 3 |
+
"B-changing value",
|
| 4 |
+
"I-changing value",
|
| 5 |
+
"B-device",
|
| 6 |
+
"I-device",
|
| 7 |
+
"B-duration",
|
| 8 |
+
"I-duration",
|
| 9 |
+
"B-living_space",
|
| 10 |
+
"I-living_space",
|
| 11 |
+
"B-target number",
|
| 12 |
+
"I-target number",
|
| 13 |
+
"B-time at",
|
| 14 |
+
"I-time at"
|
| 15 |
+
]
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": "<mask>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "</s>",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"mask_token": "<mask>",
|
| 7 |
+
"model_max_length": 256,
|
| 8 |
+
"pad_token": "<pad>",
|
| 9 |
+
"sep_token": "</s>",
|
| 10 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|