initial commit; fine-tuned on POSP
Browse files- config.json +83 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indonesian-roberta-base-posp-tagger",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10",
|
25 |
+
"11": "LABEL_11",
|
26 |
+
"12": "LABEL_12",
|
27 |
+
"13": "LABEL_13",
|
28 |
+
"14": "LABEL_14",
|
29 |
+
"15": "LABEL_15",
|
30 |
+
"16": "LABEL_16",
|
31 |
+
"17": "LABEL_17",
|
32 |
+
"18": "LABEL_18",
|
33 |
+
"19": "LABEL_19",
|
34 |
+
"20": "LABEL_20",
|
35 |
+
"21": "LABEL_21",
|
36 |
+
"22": "LABEL_22",
|
37 |
+
"23": "LABEL_23",
|
38 |
+
"24": "LABEL_24",
|
39 |
+
"25": "LABEL_25"
|
40 |
+
},
|
41 |
+
"initializer_range": 0.02,
|
42 |
+
"intermediate_size": 3072,
|
43 |
+
"label2id": {
|
44 |
+
"LABEL_0": 0,
|
45 |
+
"LABEL_1": 1,
|
46 |
+
"LABEL_10": 10,
|
47 |
+
"LABEL_11": 11,
|
48 |
+
"LABEL_12": 12,
|
49 |
+
"LABEL_13": 13,
|
50 |
+
"LABEL_14": 14,
|
51 |
+
"LABEL_15": 15,
|
52 |
+
"LABEL_16": 16,
|
53 |
+
"LABEL_17": 17,
|
54 |
+
"LABEL_18": 18,
|
55 |
+
"LABEL_19": 19,
|
56 |
+
"LABEL_2": 2,
|
57 |
+
"LABEL_20": 20,
|
58 |
+
"LABEL_21": 21,
|
59 |
+
"LABEL_22": 22,
|
60 |
+
"LABEL_23": 23,
|
61 |
+
"LABEL_24": 24,
|
62 |
+
"LABEL_25": 25,
|
63 |
+
"LABEL_3": 3,
|
64 |
+
"LABEL_4": 4,
|
65 |
+
"LABEL_5": 5,
|
66 |
+
"LABEL_6": 6,
|
67 |
+
"LABEL_7": 7,
|
68 |
+
"LABEL_8": 8,
|
69 |
+
"LABEL_9": 9
|
70 |
+
},
|
71 |
+
"layer_norm_eps": 1e-05,
|
72 |
+
"max_position_embeddings": 514,
|
73 |
+
"model_type": "roberta",
|
74 |
+
"num_attention_heads": 12,
|
75 |
+
"num_hidden_layers": 12,
|
76 |
+
"pad_token_id": 1,
|
77 |
+
"position_embedding_type": "absolute",
|
78 |
+
"torch_dtype": "float32",
|
79 |
+
"transformers_version": "4.8.2",
|
80 |
+
"type_vocab_size": 1,
|
81 |
+
"use_cache": true,
|
82 |
+
"vocab_size": 50265
|
83 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e6a75be4c1936c798d5e692d171c524005239afae0c9e68c24af10bea7256b8
|
3 |
+
size 496384817
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "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 sha256:705d171e8bec7a2e53e52d95f95182c739ae45ce244c1d897339aef9fba88b9a
|
3 |
+
size 496587920
|
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": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "flax-community/indonesian-roberta-base", "tokenizer_class": "RobertaTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|