Initial ALBERT Tiny model
Browse files- config.json +50 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "malay-huggingface/albert-tiny-bahasa-cased",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"embedding_size": 128,
|
10 |
+
"eos_token_id": 3,
|
11 |
+
"finetuning_task": "ner",
|
12 |
+
"hidden_act": "gelu_new",
|
13 |
+
"hidden_dropout_prob": 0,
|
14 |
+
"hidden_size": 336,
|
15 |
+
"id2label": {
|
16 |
+
"0": "0,",
|
17 |
+
"1": "0.",
|
18 |
+
"2": "00",
|
19 |
+
"3": "0?",
|
20 |
+
"4": "U,",
|
21 |
+
"5": "U.",
|
22 |
+
"6": "U0",
|
23 |
+
"7": "U?"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"inner_group_num": 1,
|
27 |
+
"intermediate_size": 1344,
|
28 |
+
"label2id": {
|
29 |
+
"0,": 0,
|
30 |
+
"0.": 1,
|
31 |
+
"00": 2,
|
32 |
+
"0?": 3,
|
33 |
+
"U,": 4,
|
34 |
+
"U.": 5,
|
35 |
+
"U0": 6,
|
36 |
+
"U?": 7
|
37 |
+
},
|
38 |
+
"layer_norm_eps": 1e-12,
|
39 |
+
"max_position_embeddings": 512,
|
40 |
+
"model_type": "albert",
|
41 |
+
"num_attention_heads": 12,
|
42 |
+
"num_hidden_groups": 1,
|
43 |
+
"num_hidden_layers": 4,
|
44 |
+
"pad_token_id": 0,
|
45 |
+
"position_embedding_type": "absolute",
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.13.0.dev0",
|
48 |
+
"type_vocab_size": 2,
|
49 |
+
"vocab_size": 32000
|
50 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a99475cf1422ce6b5293c7d195e960e435c66868bf8d65be6971ef0bee0bbaca
|
3 |
+
size 22283031
|
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": true}}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bb5d87a54a9cfe052ede7214cd4b21f46bc6dca3b09b33bddb7a8c5001df371
|
3 |
+
size 793955
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "remove_space": true, "keep_accents": false, "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": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "/root/.cache/huggingface/transformers/61e11849a832cf0858036414a754a64d65c79963006b95a39f8051e1577b322a.15ed5b79b197b4fcc5f3f80b2ee89a5a3ad708dbd076575cd22cffd9e1a56284", "name_or_path": "malay-huggingface/albert-tiny-bahasa-cased", "tokenizer_class": "AlbertTokenizer"}
|