Upload 7 files
Browse files- config.json +60 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/gpfs/projects/bsc88/projects/catalan_evaluation/models/roberta-base-ca-v2",
|
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 |
+
"finetuning_task": "wikicat",
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "Ci\u00e8ncia_i_Tecnologia",
|
17 |
+
"1": "Dret",
|
18 |
+
"2": "Economia",
|
19 |
+
"3": "Enginyeria",
|
20 |
+
"4": "Entreteniment",
|
21 |
+
"5": "Esport",
|
22 |
+
"6": "Filosofia",
|
23 |
+
"7": "Hist\u00f2ria",
|
24 |
+
"8": "Humanitats",
|
25 |
+
"9": "Matem\u00e0tiques",
|
26 |
+
"10": "M\u00fasica",
|
27 |
+
"11": "Pol\u00edtica",
|
28 |
+
"12": "Religi\u00f3"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"Ci\u00e8ncia_i_Tecnologia": 0,
|
34 |
+
"Dret": 1,
|
35 |
+
"Economia": 2,
|
36 |
+
"Enginyeria": 3,
|
37 |
+
"Entreteniment": 4,
|
38 |
+
"Esport": 5,
|
39 |
+
"Filosofia": 6,
|
40 |
+
"Hist\u00f2ria": 7,
|
41 |
+
"Humanitats": 8,
|
42 |
+
"Matem\u00e0tiques": 9,
|
43 |
+
"M\u00fasica": 10,
|
44 |
+
"Pol\u00edtica": 11,
|
45 |
+
"Religi\u00f3": 12
|
46 |
+
},
|
47 |
+
"layer_norm_eps": 1e-05,
|
48 |
+
"max_position_embeddings": 514,
|
49 |
+
"model_type": "roberta",
|
50 |
+
"num_attention_heads": 12,
|
51 |
+
"num_hidden_layers": 12,
|
52 |
+
"pad_token_id": 1,
|
53 |
+
"position_embedding_type": "absolute",
|
54 |
+
"problem_type": "single_label_classification",
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.17.0",
|
57 |
+
"type_vocab_size": 1,
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 50262
|
60 |
+
}
|
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 sha256:3d1f8dcc97d0db465b53798d0f5ca7cb4dec82cf9bc9ba8ca0e0cfa877aa2f57
|
3 |
+
size 498699629
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "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 |
+
{"errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "trim_offsets": true, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "/gpfs/projects/bsc88/projects/catalan_evaluation/models/roberta-base-ca-v2", "tokenizer_class": "RobertaTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|