model used join dataset based on "bert-base-multilingual-cased"
Browse files- config.json +32 -52
- model.safetensors +2 -2
- tokenizer.json +2 -2
config.json
CHANGED
|
@@ -9,62 +9,42 @@
|
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
-
"0": "
|
| 13 |
-
"1": "
|
| 14 |
-
"2": "
|
| 15 |
-
"3": "
|
| 16 |
-
"4": "
|
| 17 |
-
"5": "
|
| 18 |
-
"6": "
|
| 19 |
-
"7": "
|
| 20 |
-
"8": "
|
| 21 |
-
"9": "
|
| 22 |
-
"10": "
|
| 23 |
-
"11": "
|
| 24 |
-
"12": "
|
| 25 |
-
"13": "
|
| 26 |
-
"14": "
|
| 27 |
-
"15": "
|
| 28 |
-
"16": "PROPN",
|
| 29 |
-
"17": "NUM",
|
| 30 |
-
"18": "ONM",
|
| 31 |
-
"19": "INTW",
|
| 32 |
-
"20": "ADP",
|
| 33 |
-
"21": "PRON",
|
| 34 |
-
"22": "PUNCT",
|
| 35 |
-
"23": "SYM",
|
| 36 |
-
"24": "VERB",
|
| 37 |
-
"25": "AUX"
|
| 38 |
},
|
| 39 |
"initializer_range": 0.02,
|
| 40 |
"intermediate_size": 3072,
|
| 41 |
"label2id": {
|
| 42 |
-
"
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
-
"
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
"INTW": 19,
|
| 59 |
-
"NOUN": 15,
|
| 60 |
-
"NUM": 17,
|
| 61 |
-
"ONM": 18,
|
| 62 |
-
"PRON": 21,
|
| 63 |
-
"PROPN": 16,
|
| 64 |
-
"PUNCT": 22,
|
| 65 |
-
"SYM": 23,
|
| 66 |
-
"VERB": 24,
|
| 67 |
-
"``": 9
|
| 68 |
},
|
| 69 |
"layer_norm_eps": 1e-12,
|
| 70 |
"max_position_embeddings": 512,
|
|
|
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
+
"0": "ADJ",
|
| 13 |
+
"1": "ADP",
|
| 14 |
+
"2": "ADV",
|
| 15 |
+
"3": "AUX",
|
| 16 |
+
"4": "CONJ",
|
| 17 |
+
"5": "DET",
|
| 18 |
+
"6": "INTJ",
|
| 19 |
+
"7": "INTW",
|
| 20 |
+
"8": "NOUN",
|
| 21 |
+
"9": "NUM",
|
| 22 |
+
"10": "ONM",
|
| 23 |
+
"11": "PRON",
|
| 24 |
+
"12": "PROPN",
|
| 25 |
+
"13": "PUNCT",
|
| 26 |
+
"14": "SYM",
|
| 27 |
+
"15": "VERB"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
},
|
| 29 |
"initializer_range": 0.02,
|
| 30 |
"intermediate_size": 3072,
|
| 31 |
"label2id": {
|
| 32 |
+
"ADJ": 0,
|
| 33 |
+
"ADP": 1,
|
| 34 |
+
"ADV": 2,
|
| 35 |
+
"AUX": 3,
|
| 36 |
+
"CONJ": 4,
|
| 37 |
+
"DET": 5,
|
| 38 |
+
"INTJ": 6,
|
| 39 |
+
"INTW": 7,
|
| 40 |
+
"NOUN": 8,
|
| 41 |
+
"NUM": 9,
|
| 42 |
+
"ONM": 10,
|
| 43 |
+
"PRON": 11,
|
| 44 |
+
"PROPN": 12,
|
| 45 |
+
"PUNCT": 13,
|
| 46 |
+
"SYM": 14,
|
| 47 |
+
"VERB": 15
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
},
|
| 49 |
"layer_norm_eps": 1e-12,
|
| 50 |
"max_position_embeddings": 512,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeaa127085aa75b805d1c10e75f70573acdda28cefcfbc200db9a26dff45073d
|
| 3 |
+
size 709123968
|
tokenizer.json
CHANGED
|
@@ -2,13 +2,13 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
-
"Fixed":
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 64,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
+
"Fixed": 64
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|