Update spaCy pipeline
Browse files- README.md +9 -9
- config.cfg +1 -1
- is_ner_mim_trf-any-py3-none-any.whl +2 -2
- meta.json +31 -31
- ner/model +1 -1
- transformer/model/config.json +3 -3
- transformer/model/merges.txt +0 -0
- transformer/model/pytorch_model.bin +2 -2
- transformer/model/special_tokens_map.json +1 -1
- transformer/model/tokenizer.json +0 -0
- transformer/model/tokenizer_config.json +1 -1
- transformer/model/vocab.json +0 -0
README.md
CHANGED
@@ -13,18 +13,18 @@ model-index:
|
|
13 |
metrics:
|
14 |
- name: NER Precision
|
15 |
type: precision
|
16 |
-
value: 0.
|
17 |
- name: NER Recall
|
18 |
type: recall
|
19 |
-
value: 0.
|
20 |
- name: NER F Score
|
21 |
type: f_score
|
22 |
-
value: 0.
|
23 |
---
|
24 |
| Feature | Description |
|
25 |
| --- | --- |
|
26 |
| **Name** | `is_ner_mim_trf` |
|
27 |
-
| **Version** | `0.0.
|
28 |
| **spaCy** | `>=3.1.1,<3.2.0` |
|
29 |
| **Default Pipeline** | `transformer`, `ner` |
|
30 |
| **Components** | `transformer`, `ner` |
|
@@ -49,8 +49,8 @@ model-index:
|
|
49 |
|
50 |
| Type | Score |
|
51 |
| --- | --- |
|
52 |
-
| `ENTS_F` |
|
53 |
-
| `ENTS_P` |
|
54 |
-
| `ENTS_R` |
|
55 |
-
| `TRANSFORMER_LOSS` |
|
56 |
-
| `NER_LOSS` |
|
|
|
13 |
metrics:
|
14 |
- name: NER Precision
|
15 |
type: precision
|
16 |
+
value: 0.9193318395
|
17 |
- name: NER Recall
|
18 |
type: recall
|
19 |
+
value: 0.9217728758
|
20 |
- name: NER F Score
|
21 |
type: f_score
|
22 |
+
value: 0.9205507394
|
23 |
---
|
24 |
| Feature | Description |
|
25 |
| --- | --- |
|
26 |
| **Name** | `is_ner_mim_trf` |
|
27 |
+
| **Version** | `0.0.1` |
|
28 |
| **spaCy** | `>=3.1.1,<3.2.0` |
|
29 |
| **Default Pipeline** | `transformer`, `ner` |
|
30 |
| **Components** | `transformer`, `ner` |
|
|
|
49 |
|
50 |
| Type | Score |
|
51 |
| --- | --- |
|
52 |
+
| `ENTS_F` | 92.06 |
|
53 |
+
| `ENTS_P` | 91.93 |
|
54 |
+
| `ENTS_R` | 92.18 |
|
55 |
+
| `TRANSFORMER_LOSS` | 248325.98 |
|
56 |
+
| `NER_LOSS` | 120059.07 |
|
config.cfg
CHANGED
@@ -48,7 +48,7 @@ set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotati
|
|
48 |
|
49 |
[components.transformer.model]
|
50 |
@architectures = "spacy-transformers.TransformerModel.v1"
|
51 |
-
name = "
|
52 |
|
53 |
[components.transformer.model.get_spans]
|
54 |
@span_getters = "spacy-transformers.strided_spans.v1"
|
|
|
48 |
|
49 |
[components.transformer.model]
|
50 |
@architectures = "spacy-transformers.TransformerModel.v1"
|
51 |
+
name = "mideind/IceBERT"
|
52 |
|
53 |
[components.transformer.model.get_spans]
|
54 |
@span_getters = "spacy-transformers.strided_spans.v1"
|
is_ner_mim_trf-any-py3-none-any.whl
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 sha256:88d82cebbe11ad9aad5c9775a07c41124ec4fc31c2bfc7c8cc226824f5cccb7e
|
3 |
+
size 459577898
|
meta.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"lang":"is",
|
3 |
"name":"ner_mim_trf",
|
4 |
-
"version":"0.0.
|
5 |
"description":"",
|
6 |
"author":"",
|
7 |
"email":"",
|
8 |
"url":"",
|
9 |
"license":"",
|
10 |
"spacy_version":">=3.1.1,<3.2.0",
|
11 |
-
"spacy_git_version":"
|
12 |
"vectors":{
|
13 |
"width":0,
|
14 |
"vectors":0,
|
@@ -45,52 +45,52 @@
|
|
45 |
|
46 |
},
|
47 |
"performance":{
|
48 |
-
"ents_f":0.
|
49 |
-
"ents_p":0.
|
50 |
-
"ents_r":0.
|
51 |
"ents_per_type":{
|
52 |
"Organization":{
|
53 |
-
"p":0.
|
54 |
-
"r":0.
|
55 |
-
"f":0.
|
56 |
},
|
57 |
"Location":{
|
58 |
-
"p":0.
|
59 |
-
"r":0.
|
60 |
-
"f":0.
|
61 |
},
|
62 |
"Miscellaneous":{
|
63 |
-
"p":0.
|
64 |
-
"r":0.
|
65 |
-
"f":0.
|
66 |
},
|
67 |
"Person":{
|
68 |
-
"p":0.
|
69 |
-
"r":0.
|
70 |
-
"f":0.
|
71 |
},
|
72 |
"Date":{
|
73 |
-
"p":0.
|
74 |
-
"r":0.
|
75 |
-
"f":0.
|
76 |
},
|
77 |
"Money":{
|
78 |
-
"p":0.
|
79 |
-
"r":0.
|
80 |
-
"f":0.
|
81 |
},
|
82 |
"Time":{
|
83 |
-
"p":0.
|
84 |
-
"r":0.
|
85 |
-
"f":0.
|
86 |
},
|
87 |
"Percent":{
|
88 |
-
"p":0.
|
89 |
-
"r":0.
|
90 |
-
"f":0.
|
91 |
}
|
92 |
},
|
93 |
-
"transformer_loss":
|
94 |
-
"ner_loss":
|
95 |
}
|
96 |
}
|
|
|
1 |
{
|
2 |
"lang":"is",
|
3 |
"name":"ner_mim_trf",
|
4 |
+
"version":"0.0.1",
|
5 |
"description":"",
|
6 |
"author":"",
|
7 |
"email":"",
|
8 |
"url":"",
|
9 |
"license":"",
|
10 |
"spacy_version":">=3.1.1,<3.2.0",
|
11 |
+
"spacy_git_version":"ffaead8fe",
|
12 |
"vectors":{
|
13 |
"width":0,
|
14 |
"vectors":0,
|
|
|
45 |
|
46 |
},
|
47 |
"performance":{
|
48 |
+
"ents_f":0.9205507394,
|
49 |
+
"ents_p":0.9193318395,
|
50 |
+
"ents_r":0.9217728758,
|
51 |
"ents_per_type":{
|
52 |
"Organization":{
|
53 |
+
"p":0.9057888763,
|
54 |
+
"r":0.875,
|
55 |
+
"f":0.8901282766
|
56 |
},
|
57 |
"Location":{
|
58 |
+
"p":0.9245495495,
|
59 |
+
"r":0.9436781609,
|
60 |
+
"f":0.9340159272
|
61 |
},
|
62 |
"Miscellaneous":{
|
63 |
+
"p":0.8373860182,
|
64 |
+
"r":0.8236173393,
|
65 |
+
"f":0.8304446119
|
66 |
},
|
67 |
"Person":{
|
68 |
+
"p":0.951946472,
|
69 |
+
"r":0.9607120933,
|
70 |
+
"f":0.9563091965
|
71 |
},
|
72 |
"Date":{
|
73 |
+
"p":0.9265232975,
|
74 |
+
"r":0.9503676471,
|
75 |
+
"f":0.9382940109
|
76 |
},
|
77 |
"Money":{
|
78 |
+
"p":0.8901098901,
|
79 |
+
"r":0.9418604651,
|
80 |
+
"f":0.9152542373
|
81 |
},
|
82 |
"Time":{
|
83 |
+
"p":0.9380530973,
|
84 |
+
"r":0.954954955,
|
85 |
+
"f":0.9464285714
|
86 |
},
|
87 |
"Percent":{
|
88 |
+
"p":0.9736842105,
|
89 |
+
"r":0.9866666667,
|
90 |
+
"f":0.9801324503
|
91 |
}
|
92 |
},
|
93 |
+
"transformer_loss":2483.2597508011,
|
94 |
+
"ner_loss":1200.5906777256
|
95 |
}
|
96 |
}
|
ner/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 251051
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f003ff50afc73e6063b0aba491562c8857a56b9ef9322bb4c5a22f00341dba9a
|
3 |
size 251051
|
transformer/model/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"RobertaForMaskedLM"
|
5 |
],
|
@@ -19,8 +19,8 @@
|
|
19 |
"num_hidden_layers": 12,
|
20 |
"pad_token_id": 1,
|
21 |
"position_embedding_type": "absolute",
|
22 |
-
"transformers_version": "4.
|
23 |
"type_vocab_size": 1,
|
24 |
"use_cache": true,
|
25 |
-
"vocab_size":
|
26 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "mideind/IceBERT",
|
3 |
"architectures": [
|
4 |
"RobertaForMaskedLM"
|
5 |
],
|
|
|
19 |
"num_hidden_layers": 12,
|
20 |
"pad_token_id": 1,
|
21 |
"position_embedding_type": "absolute",
|
22 |
+
"transformers_version": "4.5.1",
|
23 |
"type_vocab_size": 1,
|
24 |
"use_cache": true,
|
25 |
+
"vocab_size": 50000
|
26 |
}
|
transformer/model/merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
transformer/model/pytorch_model.bin
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 sha256:4e91a1e7a06d166bbcac11e36d57b9fd5c6d36af5555dad92a75886fc353023c
|
3 |
+
size 497849841
|
transformer/model/special_tokens_map.json
CHANGED
@@ -1 +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":
|
|
|
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}}
|
transformer/model/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
transformer/model/tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "
|
|
|
1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "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"}, "add_prefix_space": false, "errors": "replace", "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"}, "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"}, "special_tokens_map_file": "/home/elias/.cache/huggingface/transformers/b21a20c1d1a8c4ce0f3f9b2a311ea6fa001eaaaee064c36040b1c5885cdc73f0.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0", "name_or_path": "mideind/IceBERT"}
|
transformer/model/vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|