Upload 6 files
Browse files- config.json +39 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +62 -0
- tokenizer.json +0 -0
- tokenizer_config.json +20 -0
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "zurichNLP/swissbert",
|
3 |
+
"adapter_layer_norm": false,
|
4 |
+
"adapter_reduction_factor": 2,
|
5 |
+
"adapter_reuse_layer_norm": true,
|
6 |
+
"architectures": [
|
7 |
+
"XmodForCL"
|
8 |
+
],
|
9 |
+
"attention_probs_dropout_prob": 0.1,
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"classifier_dropout": null,
|
12 |
+
"default_language": "de_CH",
|
13 |
+
"eos_token_id": 2,
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_dropout_prob": 0.1,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"languages": [
|
20 |
+
"de_CH",
|
21 |
+
"fr_CH",
|
22 |
+
"it_CH",
|
23 |
+
"rm_CH"
|
24 |
+
],
|
25 |
+
"layer_norm_eps": 1e-05,
|
26 |
+
"ln_before_adapter": true,
|
27 |
+
"max_position_embeddings": 514,
|
28 |
+
"model_type": "xmod",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"pre_norm": false,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.30.2",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50262
|
39 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:701e892c170bc8e650df424af9a16facaed15231f5f2769b358ecaaab7910ce1
|
3 |
+
size 609820197
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90f13e153795f964755c7f354690628ad7415b2de7abeb82b82035433c9d53a0
|
3 |
+
size 1158958
|
special_tokens_map.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<medium>",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<year>",
|
12 |
+
"lstrip": true,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "<month>",
|
19 |
+
"lstrip": true,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"bos_token": {
|
26 |
+
"content": "<s>",
|
27 |
+
"lstrip": true,
|
28 |
+
"normalized": true,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
},
|
32 |
+
"cls_token": {
|
33 |
+
"content": "<s>",
|
34 |
+
"lstrip": true,
|
35 |
+
"normalized": true,
|
36 |
+
"rstrip": false,
|
37 |
+
"single_word": false
|
38 |
+
},
|
39 |
+
"eos_token": {
|
40 |
+
"content": "</s>",
|
41 |
+
"lstrip": true,
|
42 |
+
"normalized": true,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"mask_token": {
|
47 |
+
"content": "<mask>",
|
48 |
+
"lstrip": true,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false
|
52 |
+
},
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": {
|
55 |
+
"content": "</s>",
|
56 |
+
"lstrip": true,
|
57 |
+
"normalized": true,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false
|
60 |
+
},
|
61 |
+
"unk_token": "<unk>"
|
62 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 512,
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"sp_model_kwargs": {},
|
18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|