vesteinn
commited on
Commit
•
6b6f3f8
0
Parent(s):
Added model
Browse files- .gitattributes +3 -0
- config.json +66 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
.gitattributes
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
2 |
+
training_args.bin filter=lfs diff=lfs merge=lfs -text
|
3 |
+
sentencepiece.bpe.model filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vesteinn/ScandiBERT",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForTokenClassification"
|
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": "O",
|
16 |
+
"1": "B-Date",
|
17 |
+
"2": "B-Location",
|
18 |
+
"3": "B-Miscellaneous",
|
19 |
+
"4": "B-Money",
|
20 |
+
"5": "B-Organization",
|
21 |
+
"6": "B-Percent",
|
22 |
+
"7": "B-Person",
|
23 |
+
"8": "B-Time",
|
24 |
+
"9": "I-Date",
|
25 |
+
"10": "I-Location",
|
26 |
+
"11": "I-Miscellaneous",
|
27 |
+
"12": "I-Money",
|
28 |
+
"13": "I-Organization",
|
29 |
+
"14": "I-Percent",
|
30 |
+
"15": "I-Person",
|
31 |
+
"16": "I-Time"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
+
"label2id": {
|
36 |
+
"LABEL_0": 0,
|
37 |
+
"LABEL_1": 1,
|
38 |
+
"LABEL_10": 10,
|
39 |
+
"LABEL_11": 11,
|
40 |
+
"LABEL_12": 12,
|
41 |
+
"LABEL_13": 13,
|
42 |
+
"LABEL_14": 14,
|
43 |
+
"LABEL_15": 15,
|
44 |
+
"LABEL_16": 16,
|
45 |
+
"LABEL_2": 2,
|
46 |
+
"LABEL_3": 3,
|
47 |
+
"LABEL_4": 4,
|
48 |
+
"LABEL_5": 5,
|
49 |
+
"LABEL_6": 6,
|
50 |
+
"LABEL_7": 7,
|
51 |
+
"LABEL_8": 8,
|
52 |
+
"LABEL_9": 9
|
53 |
+
},
|
54 |
+
"layer_norm_eps": 1e-05,
|
55 |
+
"max_position_embeddings": 514,
|
56 |
+
"model_type": "xlm-roberta",
|
57 |
+
"num_attention_heads": 12,
|
58 |
+
"num_hidden_layers": 12,
|
59 |
+
"pad_token_id": 1,
|
60 |
+
"position_embedding_type": "absolute",
|
61 |
+
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.15.0",
|
63 |
+
"type_vocab_size": 1,
|
64 |
+
"use_cache": true,
|
65 |
+
"vocab_size": 50005
|
66 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca6c9151533dcbe7dbafa5dee632acd51b207d6a557dd6d76f978f619fb1b3f3
|
3 |
+
size 495558449
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fca70379c621cffc6910d3988182faedd75c5b01a8adcb552405a8f83ce7a41
|
3 |
+
size 1084241
|
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": true}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "vesteinn/ScandiBERT", "sp_model_kwargs": {}, "add_prefix_space": true, "tokenizer_class": "XLMRobertaTokenizer"}
|