Upload 13 files
Browse files- .gitattributes +2 -0
- CHANGELOG.md +4 -0
- LICENSE +22 -0
- NOTICE +6 -0
- README.md +101 -0
- config.json +26 -0
- config_sentence_transformers.json +7 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +64 -0
- unigram.json +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ 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
|
37 |
+
unigram.json filter=lfs diff=lfs merge=lfs -text
|
CHANGELOG.md
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Changelog
|
2 |
+
|
3 |
+
## v0.1 - 2024-04-07 - @0xnu
|
4 |
+
* Initial release.
|
LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
0xnu/pmmlv2-fine-tuned-hausa
|
2 |
+
Copyright (c) 2024 Finbarrs Oketunji.
|
3 |
+
|
4 |
+
MIT License
|
5 |
+
|
6 |
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
7 |
+
of this software and associated documentation files (the "Software"), to deal
|
8 |
+
in the Software without restriction, including without limitation the rights
|
9 |
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
10 |
+
copies of the Software, and to permit persons to whom the Software is
|
11 |
+
furnished to do so, subject to the following conditions:
|
12 |
+
|
13 |
+
The above copyright notice and this permission notice shall be included in all
|
14 |
+
copies or substantial portions of the Software.
|
15 |
+
|
16 |
+
THE SOFTWARE IS PROVIDED *AS IS*, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
17 |
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
18 |
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
19 |
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
20 |
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
21 |
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
22 |
+
SOFTWARE.
|
NOTICE
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
@name: 0xnu/pmmlv2-fine-tuned-hausa
|
2 |
+
@author: Finbarrs Oketunji
|
3 |
+
@contact: [email protected]
|
4 |
+
@time: 07/04/2024 - 00:33:10
|
5 |
+
|
6 |
+
This product includes software developed by [Finbarrs Oketunji](https://finbarrs.eu).
|
README.md
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- multilingual
|
4 |
+
- ar
|
5 |
+
- bg
|
6 |
+
- ca
|
7 |
+
- cs
|
8 |
+
- da
|
9 |
+
- de
|
10 |
+
- el
|
11 |
+
- en
|
12 |
+
- es
|
13 |
+
- et
|
14 |
+
- fa
|
15 |
+
- fi
|
16 |
+
- fr
|
17 |
+
- gl
|
18 |
+
- gu
|
19 |
+
- he
|
20 |
+
- hi
|
21 |
+
- hr
|
22 |
+
- hu
|
23 |
+
- hy
|
24 |
+
- id
|
25 |
+
- it
|
26 |
+
- ja
|
27 |
+
- ka
|
28 |
+
- ko
|
29 |
+
- ku
|
30 |
+
- lt
|
31 |
+
- lv
|
32 |
+
- mk
|
33 |
+
- mn
|
34 |
+
- mr
|
35 |
+
- ms
|
36 |
+
- my
|
37 |
+
- nb
|
38 |
+
- nl
|
39 |
+
- pl
|
40 |
+
- pt
|
41 |
+
- ro
|
42 |
+
- ru
|
43 |
+
- sk
|
44 |
+
- sl
|
45 |
+
- sq
|
46 |
+
- sr
|
47 |
+
- sv
|
48 |
+
- th
|
49 |
+
- tr
|
50 |
+
- uk
|
51 |
+
- ur
|
52 |
+
- vi
|
53 |
+
- ha
|
54 |
+
license: mit
|
55 |
+
library_name: sentence-transformers
|
56 |
+
tags:
|
57 |
+
- sentence-transformers
|
58 |
+
- feature-extraction
|
59 |
+
- sentence-similarity
|
60 |
+
- transformers
|
61 |
+
language_bcp47:
|
62 |
+
- fr-ca
|
63 |
+
- pt-br
|
64 |
+
- zh-cn
|
65 |
+
- zh-tw
|
66 |
+
pipeline_tag: sentence-similarity
|
67 |
+
inference: false
|
68 |
+
---
|
69 |
+
|
70 |
+
## 0xnu/pmmlv2-fine-tuned-hausa
|
71 |
+
|
72 |
+
Hausa fine-tuned LLM using [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2).
|
73 |
+
|
74 |
+
[Hausa](https://en.wikipedia.org/wiki/Hausa_language) words typically comprise diverse blends of vowels and consonants. The Hausa language boasts a vibrant phonetic framework featuring twenty-three consonants, five vowels, and two diphthongs. Words in Hausa can fluctuate in length and intricacy, but they usually adhere to uniform configurations of syllable arrangement and articulation. Additionally, Hausa words often incorporate diacritical marks like the apostrophe and macron to signify glottal stops and long vowels.
|
75 |
+
|
76 |
+
### Usage (Sentence-Transformers)
|
77 |
+
|
78 |
+
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
79 |
+
|
80 |
+
```
|
81 |
+
pip install -U sentence-transformers
|
82 |
+
```
|
83 |
+
|
84 |
+
Then you can use the model like this:
|
85 |
+
|
86 |
+
```python
|
87 |
+
from sentence_transformers import SentenceTransformer
|
88 |
+
sentences = ["Met de deur in huis vallen", "Niet geschoten is altijd mis"]
|
89 |
+
|
90 |
+
model = SentenceTransformer('0xnu/pmmlv2-fine-tuned-hausa')
|
91 |
+
embeddings = model.encode(sentences)
|
92 |
+
print(embeddings)
|
93 |
+
```
|
94 |
+
|
95 |
+
### License
|
96 |
+
|
97 |
+
This project is licensed under the [MIT License](./LICENSE).
|
98 |
+
|
99 |
+
### Copyright
|
100 |
+
|
101 |
+
(c) 2024 [Finbarrs Oketunji](https://finbarrs.eu).
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "models/0xnu/pmmlv2-fine-tuned-hausa/",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 384,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1536,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.38.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 250037
|
26 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.0.0",
|
4 |
+
"transformers": "4.7.0",
|
5 |
+
"pytorch": "1.9.0+cu102"
|
6 |
+
}
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60b6fde8416b3e0ef94c97018033718a5de4afe0ce3bb852fa84d701f9623229
|
3 |
+
size 470637416
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 128,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa685fc160bbdbab64058d4fc91b60e62d207e8dc60b9af5c002c5ab946ded00
|
3 |
+
size 17083009
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"mask_token": "<mask>",
|
50 |
+
"max_length": 128,
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "</s>",
|
57 |
+
"stride": 0,
|
58 |
+
"strip_accents": null,
|
59 |
+
"tokenize_chinese_chars": true,
|
60 |
+
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "<unk>"
|
64 |
+
}
|
unigram.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
|
3 |
+
size 14763260
|