Upload model
Browse files- .gitattributes +1 -0
- config.json +124 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +20 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
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 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "adj.all",
|
15 |
+
"1": "noun.attribute",
|
16 |
+
"2": "0",
|
17 |
+
"3": "noun.time",
|
18 |
+
"4": "noun.artifact",
|
19 |
+
"5": "verb.stative",
|
20 |
+
"6": "noun.body",
|
21 |
+
"7": "verb.possession",
|
22 |
+
"8": "noun.cognition",
|
23 |
+
"9": "noun.substance",
|
24 |
+
"10": "adv.all",
|
25 |
+
"11": "verb.social",
|
26 |
+
"12": "verb.perception",
|
27 |
+
"13": "verb.contact",
|
28 |
+
"14": "noun.state",
|
29 |
+
"15": "noun.location",
|
30 |
+
"16": "noun.quantity",
|
31 |
+
"17": "noun.Tops",
|
32 |
+
"18": "verb.change",
|
33 |
+
"19": "noun.group",
|
34 |
+
"20": "noun.feeling",
|
35 |
+
"21": "adj.pert",
|
36 |
+
"22": "noun.food",
|
37 |
+
"23": "verb.cognition",
|
38 |
+
"24": "noun.communication",
|
39 |
+
"25": "verb.creation",
|
40 |
+
"26": "verb.motion",
|
41 |
+
"27": "verb.body",
|
42 |
+
"28": "noun.process",
|
43 |
+
"29": "noun.person",
|
44 |
+
"30": "verb.communication",
|
45 |
+
"31": "noun.act",
|
46 |
+
"32": "noun.relation",
|
47 |
+
"33": "noun.shape",
|
48 |
+
"34": "noun.event",
|
49 |
+
"35": "noun.phenomenon",
|
50 |
+
"36": "verb.consumption",
|
51 |
+
"37": "verb.emotion",
|
52 |
+
"38": "verb.competition",
|
53 |
+
"39": "noun.possession",
|
54 |
+
"40": "noun.motive",
|
55 |
+
"41": "noun.plant",
|
56 |
+
"42": "noun.object",
|
57 |
+
"43": "noun.animal",
|
58 |
+
"44": "adj.ppl",
|
59 |
+
"45": "verb.weather"
|
60 |
+
},
|
61 |
+
"initializer_range": 0.02,
|
62 |
+
"intermediate_size": 4096,
|
63 |
+
"label2id": {
|
64 |
+
"0": 2,
|
65 |
+
"adj.all": 0,
|
66 |
+
"adj.pert": 21,
|
67 |
+
"adj.ppl": 44,
|
68 |
+
"adv.all": 10,
|
69 |
+
"noun.Tops": 17,
|
70 |
+
"noun.act": 31,
|
71 |
+
"noun.animal": 43,
|
72 |
+
"noun.artifact": 4,
|
73 |
+
"noun.attribute": 1,
|
74 |
+
"noun.body": 6,
|
75 |
+
"noun.cognition": 8,
|
76 |
+
"noun.communication": 24,
|
77 |
+
"noun.event": 34,
|
78 |
+
"noun.feeling": 20,
|
79 |
+
"noun.food": 22,
|
80 |
+
"noun.group": 19,
|
81 |
+
"noun.location": 15,
|
82 |
+
"noun.motive": 40,
|
83 |
+
"noun.object": 42,
|
84 |
+
"noun.person": 29,
|
85 |
+
"noun.phenomenon": 35,
|
86 |
+
"noun.plant": 41,
|
87 |
+
"noun.possession": 39,
|
88 |
+
"noun.process": 28,
|
89 |
+
"noun.quantity": 16,
|
90 |
+
"noun.relation": 32,
|
91 |
+
"noun.shape": 33,
|
92 |
+
"noun.state": 14,
|
93 |
+
"noun.substance": 9,
|
94 |
+
"noun.time": 3,
|
95 |
+
"verb.body": 27,
|
96 |
+
"verb.change": 18,
|
97 |
+
"verb.cognition": 23,
|
98 |
+
"verb.communication": 30,
|
99 |
+
"verb.competition": 38,
|
100 |
+
"verb.consumption": 36,
|
101 |
+
"verb.contact": 13,
|
102 |
+
"verb.creation": 25,
|
103 |
+
"verb.emotion": 37,
|
104 |
+
"verb.motion": 26,
|
105 |
+
"verb.perception": 12,
|
106 |
+
"verb.possession": 7,
|
107 |
+
"verb.social": 11,
|
108 |
+
"verb.stative": 5,
|
109 |
+
"verb.weather": 45
|
110 |
+
},
|
111 |
+
"layer_norm_eps": 1e-05,
|
112 |
+
"max_position_embeddings": 514,
|
113 |
+
"model_type": "xlm-roberta",
|
114 |
+
"num_attention_heads": 16,
|
115 |
+
"num_hidden_layers": 24,
|
116 |
+
"output_past": true,
|
117 |
+
"pad_token_id": 1,
|
118 |
+
"position_embedding_type": "absolute",
|
119 |
+
"torch_dtype": "float32",
|
120 |
+
"transformers_version": "4.26.0",
|
121 |
+
"type_vocab_size": 1,
|
122 |
+
"use_cache": true,
|
123 |
+
"vocab_size": 250002
|
124 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:449ec8f8d7054976e25c37958e3bdea953bd2eef09720e370932211c23130474
|
3 |
+
size 2235685805
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
|
3 |
+
size 17082758
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"model_max_length": 512,
|
14 |
+
"name_or_path": "xlm-roberta-large",
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"special_tokens_map_file": null,
|
18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|