Commit
·
9fcb283
verified
·
0
Parent(s):
Duplicate from CohereForAI/aya-101
Browse filesCo-authored-by: Ahmet Ustun <[email protected]>
- .gitattributes +36 -0
- README.md +323 -0
- aya-fig1.png +3 -0
- config.json +33 -0
- generation_config.json +7 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +38 -0
.gitattributes
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.xz 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
|
README.md
ADDED
@@ -0,0 +1,323 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- CohereForAI/xP3x
|
5 |
+
- CohereForAI/aya_dataset
|
6 |
+
- CohereForAI/aya_collection
|
7 |
+
- DataProvenanceInitiative/Commercially-Verified-Licenses
|
8 |
+
- CohereForAI/aya_evaluation_suite
|
9 |
+
language:
|
10 |
+
- afr
|
11 |
+
- amh
|
12 |
+
- ara
|
13 |
+
- aze
|
14 |
+
- bel
|
15 |
+
- ben
|
16 |
+
- bul
|
17 |
+
- cat
|
18 |
+
- ceb
|
19 |
+
- ces
|
20 |
+
- cym
|
21 |
+
- dan
|
22 |
+
- deu
|
23 |
+
- ell
|
24 |
+
- eng
|
25 |
+
- epo
|
26 |
+
- est
|
27 |
+
- eus
|
28 |
+
- fin
|
29 |
+
- fil
|
30 |
+
- fra
|
31 |
+
- fry
|
32 |
+
- gla
|
33 |
+
- gle
|
34 |
+
- glg
|
35 |
+
- guj
|
36 |
+
- hat
|
37 |
+
- hau
|
38 |
+
- heb
|
39 |
+
- hin
|
40 |
+
- hun
|
41 |
+
- hye
|
42 |
+
- ibo
|
43 |
+
- ind
|
44 |
+
- isl
|
45 |
+
- ita
|
46 |
+
- jav
|
47 |
+
- jpn
|
48 |
+
- kan
|
49 |
+
- kat
|
50 |
+
- kaz
|
51 |
+
- khm
|
52 |
+
- kir
|
53 |
+
- kor
|
54 |
+
- kur
|
55 |
+
- lao
|
56 |
+
- lav
|
57 |
+
- lat
|
58 |
+
- lit
|
59 |
+
- ltz
|
60 |
+
- mal
|
61 |
+
- mar
|
62 |
+
- mkd
|
63 |
+
- mlg
|
64 |
+
- mlt
|
65 |
+
- mon
|
66 |
+
- mri
|
67 |
+
- msa
|
68 |
+
- mya
|
69 |
+
- nep
|
70 |
+
- nld
|
71 |
+
- nor
|
72 |
+
- nso
|
73 |
+
- nya
|
74 |
+
- ory
|
75 |
+
- pan
|
76 |
+
- pes
|
77 |
+
- pol
|
78 |
+
- por
|
79 |
+
- pus
|
80 |
+
- ron
|
81 |
+
- rus
|
82 |
+
- sin
|
83 |
+
- slk
|
84 |
+
- slv
|
85 |
+
- smo
|
86 |
+
- sna
|
87 |
+
- snd
|
88 |
+
- som
|
89 |
+
- sot
|
90 |
+
- spa
|
91 |
+
- sqi
|
92 |
+
- srp
|
93 |
+
- sun
|
94 |
+
- swa
|
95 |
+
- swe
|
96 |
+
- tam
|
97 |
+
- tel
|
98 |
+
- tgk
|
99 |
+
- tha
|
100 |
+
- tur
|
101 |
+
- twi
|
102 |
+
- ukr
|
103 |
+
- urd
|
104 |
+
- uzb
|
105 |
+
- vie
|
106 |
+
- xho
|
107 |
+
- yid
|
108 |
+
- yor
|
109 |
+
- zho
|
110 |
+
- zul
|
111 |
+
metrics:
|
112 |
+
- accuracy
|
113 |
+
- bleu
|
114 |
+
---
|
115 |
+
|
116 |
+
<img src="aya-fig1.png" alt="Aya model summary image" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
117 |
+
|
118 |
+
# Model Card for Aya 101
|
119 |
+
|
120 |
+
## Model Summary
|
121 |
+
|
122 |
+
> The Aya model is a massively multilingual generative language model that follows instructions in 101 languages.
|
123 |
+
> Aya outperforms [mT0](https://huggingface.co/bigscience/mt0-xxl) and [BLOOMZ](https://huggingface.co/bigscience/bloomz) a wide variety of automatic and human evaluations despite covering double the number of languages.
|
124 |
+
> The Aya model is trained using [xP3x](https://huggingface.co/datasets/CohereForAI/xP3x), [Aya Dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset), [Aya Collection](https://huggingface.co/datasets/CohereForAI/aya_collection), a subset of [DataProvenance collection](https://huggingface.co/datasets/DataProvenanceInitiative/Commercially-Verified-Licenses) and ShareGPT-Command.
|
125 |
+
> We release the checkpoints under a Apache-2.0 license to further our mission of multilingual technologies empowering a
|
126 |
+
> multilingual world.
|
127 |
+
|
128 |
+
- **Developed by:** [Cohere For AI]((https://cohere.for.ai))
|
129 |
+
- **Model type:** a Transformer style autoregressive massively multilingual language model.
|
130 |
+
- **Paper**: [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://arxiv.org/abs/2402.07827)
|
131 |
+
- **Point of Contact**: Cohere For AI: [cohere.for.ai](https://cohere.for.ai)
|
132 |
+
- **Languages**: Refer to the list of languages in the `language` section of this model card.
|
133 |
+
- **License**: Apache-2.0
|
134 |
+
- **Model**: [Aya-101](https://huggingface.co/CohereForAI/aya-101)
|
135 |
+
- **Model Size**: 13 billion parameters
|
136 |
+
- **Datasets**: [xP3x](https://huggingface.co/datasets/CohereForAI/xP3x), [Aya Dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset), [Aya Collection](https://huggingface.co/datasets/CohereForAI/aya_collection), [DataProvenance collection](https://huggingface.co/datasets/DataProvenanceInitiative/Commercially-Verified-Licenses), ShareGPT-Command.
|
137 |
+
|
138 |
+
## Use
|
139 |
+
|
140 |
+
```python
|
141 |
+
# pip install -q transformers
|
142 |
+
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
143 |
+
|
144 |
+
checkpoint = "CohereForAI/aya-101"
|
145 |
+
|
146 |
+
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
|
147 |
+
aya_model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
|
148 |
+
|
149 |
+
# Turkish to English translation
|
150 |
+
tur_inputs = tokenizer.encode("Translate to English: Aya cok dilli bir dil modelidir.", return_tensors="pt")
|
151 |
+
tur_outputs = aya_model.generate(tur_inputs, max_new_tokens=128)
|
152 |
+
print(tokenizer.decode(tur_outputs[0]))
|
153 |
+
# Aya is a multi-lingual language model
|
154 |
+
|
155 |
+
# Q: Why are there so many languages in India?
|
156 |
+
hin_inputs = tokenizer.encode("भारत में इतनी सारी भाषाएँ क्यों हैं?", return_tensors="pt")
|
157 |
+
hin_outputs = aya_model.generate(hin_inputs, max_new_tokens=128)
|
158 |
+
print(tokenizer.decode(hin_outputs[0]))
|
159 |
+
# Expected output: भारत में कई भाषाएँ हैं और विभिन्न भाषाओं के बोली जाने वाले लोग हैं। यह विभिन्नता भाषाई विविधता और सांस्कृतिक विविधता का परिणाम है। Translates to "India has many languages and people speaking different languages. This diversity is the result of linguistic diversity and cultural diversity."
|
160 |
+
|
161 |
+
```
|
162 |
+
|
163 |
+
## Model Details
|
164 |
+
|
165 |
+
### Finetuning
|
166 |
+
|
167 |
+
- Architecture: Same as [mt5-xxl](https://huggingface.co/google/mt5-xxl)
|
168 |
+
- Number of Samples seen during Finetuning: 25M
|
169 |
+
- Batch size: 256
|
170 |
+
- Hardware: TPUv4-128
|
171 |
+
- Software: T5X, Jax
|
172 |
+
|
173 |
+
### Data Sources
|
174 |
+
|
175 |
+
The Aya model is trained on the following datasets:
|
176 |
+
|
177 |
+
- [xP3x](https://huggingface.co/datasets/CohereForAI/xP3x)
|
178 |
+
- [Aya Dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset)
|
179 |
+
- [Aya Collection](https://huggingface.co/datasets/CohereForAI/aya_collection)
|
180 |
+
- [DataProvenance collection](https://huggingface.co/datasets/DataProvenanceInitiative/Commercially-Verified-Licenses)
|
181 |
+
- ShareGPT-Command
|
182 |
+
|
183 |
+
All datasets are subset to the 101 languages supported by [mT5](https://huggingface.co/google/mt5-xxl). See the [paper](https://arxiv.org/abs/2402.07827) for details about filtering and pruning.
|
184 |
+
|
185 |
+
## Evaluation
|
186 |
+
|
187 |
+
We refer to Section 5 from our paper for multilingual eval across 99 languages – including discriminative and generative tasks, human evaluation, and simulated win rates that cover both held-out tasks and in-distribution performance.
|
188 |
+
|
189 |
+
## Bias, Risks, and Limitations
|
190 |
+
|
191 |
+
|
192 |
+
For a detailed overview of our effort at safety mitigation and benchmarking toxicity and bias across multiple languages, we refer to Sections 6 and 7 of our paper: [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://arxiv.org/abs/2402.07827).
|
193 |
+
|
194 |
+
We hope that the release of the Aya model will make community-based redteaming efforts possible, by exposing an open-source massively-multilingual model for community research.
|
195 |
+
|
196 |
+
## Citation
|
197 |
+
|
198 |
+
**BibTeX:**
|
199 |
+
|
200 |
+
```
|
201 |
+
@article{üstün2024aya,
|
202 |
+
title={Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model},
|
203 |
+
author={Ahmet Üstün and Viraat Aryabumi and Zheng-Xin Yong and Wei-Yin Ko and Daniel D'souza and Gbemileke Onilude and Neel Bhandari and Shivalika Singh and Hui-Lee Ooi and Amr Kayid and Freddie Vargus and Phil Blunsom and Shayne Longpre and Niklas Muennighoff and Marzieh Fadaee and Julia Kreutzer and Sara Hooker},
|
204 |
+
journal={arXiv preprint arXiv:2402.07827},
|
205 |
+
year={2024}
|
206 |
+
}
|
207 |
+
```
|
208 |
+
|
209 |
+
## Languages Covered
|
210 |
+
|
211 |
+
<details>
|
212 |
+
<summary>Click to see Languages Covered</summary>
|
213 |
+
|
214 |
+
Below is the list of languages used in finetuning the Aya Model. We group languages into higher-, mid-, and lower-resourcedness based on a language classification by [Joshi et. al, 2020](https://microsoft.github.io/linguisticdiversity/). For further details, we refer to our [paper](https://arxiv.org/abs/2402.07827)
|
215 |
+
|
216 |
+
| ISO Code | Language Name | Script | Family | Subgrouping | Resourcedness |
|
217 |
+
| :------- | :-------------- | :----------: | :-------------: | :---------------: | :-----------: |
|
218 |
+
| afr | Afrikaans | Latin | Indo-European | Germanic | Mid |
|
219 |
+
| amh | Amharic | Ge'ez | Afro-Asiatic | Semitic | Low |
|
220 |
+
| ara | Arabic | Arabic | Afro-Asiatic | Semitic | High |
|
221 |
+
| aze | Azerbaijani | Arabic/Latin | Turkic | Common Turkic | Low |
|
222 |
+
| bel | Belarusian | Cyrillic | Indo-European | Balto-Slavic | Mid |
|
223 |
+
| ben | Bengali | Bengali | Indo-European | Indo-Aryan | Mid |
|
224 |
+
| bul | Bulgarian | Cyrillic | Indo-European | Balto-Slavic | Mid |
|
225 |
+
| cat | Catalan | Latin | Indo-European | Italic | High |
|
226 |
+
| ceb | Cebuano | Latin | Austronesian | Malayo-Polynesian | Mid |
|
227 |
+
| ces | Czech | Latin | Indo-European | Balto-Slavic | High |
|
228 |
+
| cym | Welsh | Latin | Indo-European | Celtic | Low |
|
229 |
+
| dan | Danish | Latin | Indo-European | Germanic | Mid |
|
230 |
+
| deu | German | Latin | Indo-European | Germanic | High |
|
231 |
+
| ell | Greek | Greek | Indo-European | Graeco-Phrygian | Mid |
|
232 |
+
| eng | English | Latin | Indo-European | Germanic | High |
|
233 |
+
| epo | Esperanto | Latin | Constructed | Esperantic | Low |
|
234 |
+
| est | Estonian | Latin | Uralic | Finnic | Mid |
|
235 |
+
| eus | Basque | Latin | Basque | - | High |
|
236 |
+
| fin | Finnish | Latin | Uralic | Finnic | High |
|
237 |
+
| fil | Tagalog | Latin | Austronesian | Malayo-Polynesian | Mid |
|
238 |
+
| fra | French | Latin | Indo-European | Italic | High |
|
239 |
+
| fry | Western Frisian | Latin | Indo-European | Germanic | Low |
|
240 |
+
| gla | Scottish Gaelic | Latin | Indo-European | Celtic | Low |
|
241 |
+
| gle | Irish | Latin | Indo-European | Celtic | Low |
|
242 |
+
| glg | Galician | Latin | Indo-European | Italic | Mid |
|
243 |
+
| guj | Gujarati | Gujarati | Indo-European | Indo-Aryan | Low |
|
244 |
+
| hat | Haitian Creole | Latin | Indo-European | Italic | Low |
|
245 |
+
| hau | Hausa | Latin | Afro-Asiatic | Chadic | Low |
|
246 |
+
| heb | Hebrew | Hebrew | Afro-Asiatic | Semitic | Mid |
|
247 |
+
| hin | Hindi | Devanagari | Indo-European | Indo-Aryan | High |
|
248 |
+
| hun | Hungarian | Latin | Uralic | - | High |
|
249 |
+
| hye | Armenian | Armenian | Indo-European | Armenic | Low |
|
250 |
+
| ibo | Igbo | Latin | Atlantic-Congo | Benue-Congo | Low |
|
251 |
+
| ind | Indonesian | Latin | Austronesian | Malayo-Polynesian | Mid |
|
252 |
+
| isl | Icelandic | Latin | Indo-European | Germanic | Low |
|
253 |
+
| ita | Italian | Latin | Indo-European | Italic | High |
|
254 |
+
| jav | Javanese | Latin | Austronesian | Malayo-Polynesian | Low |
|
255 |
+
| jpn | Japanese | Japanese | Japonic | Japanesic | High |
|
256 |
+
| kan | Kannada | Kannada | Dravidian | South Dravidian | Low |
|
257 |
+
| kat | Georgian | Georgian | Kartvelian | Georgian-Zan | Mid |
|
258 |
+
| kaz | Kazakh | Cyrillic | Turkic | Common Turkic | Mid |
|
259 |
+
| khm | Khmer | Khmer | Austroasiatic | Khmeric | Low |
|
260 |
+
| kir | Kyrgyz | Cyrillic | Turkic | Common Turkic | Low |
|
261 |
+
| kor | Korean | Hangul | Koreanic | Korean | High |
|
262 |
+
| kur | Kurdish | Latin | Indo-European | Iranian | Low |
|
263 |
+
| lao | Lao | Lao | Tai-Kadai | Kam-Tai | Low |
|
264 |
+
| lav | Latvian | Latin | Indo-European | Balto-Slavic | Mid |
|
265 |
+
| lat | Latin | Latin | Indo-European | Italic | Mid |
|
266 |
+
| lit | Lithuanian | Latin | Indo-European | Balto-Slavic | Mid |
|
267 |
+
| ltz | Luxembourgish | Latin | Indo-European | Germanic | Low |
|
268 |
+
| mal | Malayalam | Malayalam | Dravidian | South Dravidian | Low |
|
269 |
+
| mar | Marathi | Devanagari | Indo-European | Indo-Aryan | Low |
|
270 |
+
| mkd | Macedonian | Cyrillic | Indo-European | Balto-Slavic | Low |
|
271 |
+
| mlg | Malagasy | Latin | Austronesian | Malayo-Polynesian | Low |
|
272 |
+
| mlt | Maltese | Latin | Afro-Asiatic | Semitic | Low |
|
273 |
+
| mon | Mongolian | Cyrillic | Mongolic-Khitan | Mongolic | Low |
|
274 |
+
| mri | Maori | Latin | Austronesian | Malayo-Polynesian | Low |
|
275 |
+
| msa | Malay | Latin | Austronesian | Malayo-Polynesian | Mid |
|
276 |
+
| mya | Burmese | Myanmar | Sino-Tibetan | Burmo-Qiangic | Low |
|
277 |
+
| nep | Nepali | Devanagari | Indo-European | Indo-Aryan | Low |
|
278 |
+
| nld | Dutch | Latin | Indo-European | Germanic | High |
|
279 |
+
| nor | Norwegian | Latin | Indo-European | Germanic | Low |
|
280 |
+
| nso | Northern Sotho | Latin | Atlantic-Congo | Benue-Congo | Low |
|
281 |
+
| nya | Chichewa | Latin | Atlantic-Congo | Benue-Congo | Low |
|
282 |
+
| ory | Oriya | Oriya | Indo-European | Indo-Aryan | Low |
|
283 |
+
| pan | Punjabi | Gurmukhi | Indo-European | Indo-Aryan | Low |
|
284 |
+
| pes | Persian | Arabic | Indo-European | Iranian | High |
|
285 |
+
| pol | Polish | Latin | Indo-European | Balto-Slavic | High |
|
286 |
+
| por | Portuguese | Latin | Indo-European | Italic | High |
|
287 |
+
| pus | Pashto | Arabic | Indo-European | Iranian | Low |
|
288 |
+
| ron | Romanian | Latin | Indo-European | Italic | Mid |
|
289 |
+
| rus | Russian | Cyrillic | Indo-European | Balto-Slavic | High |
|
290 |
+
| sin | Sinhala | Sinhala | Indo-European | Indo-Aryan | Low |
|
291 |
+
| slk | Slovak | Latin | Indo-European | Balto-Slavic | Mid |
|
292 |
+
| slv | Slovenian | Latin | Indo-European | Balto-Slavic | Mid |
|
293 |
+
| smo | Samoan | Latin | Austronesian | Malayo-Polynesian | Low |
|
294 |
+
| sna | Shona | Latin | Indo-European | Indo-Aryan | Low |
|
295 |
+
| snd | Sindhi | Arabic | Indo-European | Indo-Aryan | Low |
|
296 |
+
| som | Somali | Latin | Afro-Asiatic | Cushitic | Low |
|
297 |
+
| sot | Southern Sotho | Latin | Atlantic-Congo | Benue-Congo | Low |
|
298 |
+
| spa | Spanish | Latin | Indo-European | Italic | High |
|
299 |
+
| sqi | Albanian | Latin | Indo-European | Albanian | Low |
|
300 |
+
| srp | Serbian | Cyrillic | Indo-European | Balto-Slavic | High |
|
301 |
+
| sun | Sundanese | Latin | Austronesian | Malayo-Polynesian | Low |
|
302 |
+
| swa | Swahili | Latin | Atlantic-Congo | Benue-Congo | Low |
|
303 |
+
| swe | Swedish | Latin | Indo-European | Germanic | High |
|
304 |
+
| tam | Tamil | Tamil | Dravidian | South Dravidian | Mid |
|
305 |
+
| tel | Telugu | Telugu | Dravidian | South Dravidian | Low |
|
306 |
+
| tgk | Tajik | Cyrillic | Indo-European | Iranian | Low |
|
307 |
+
| tha | Thai | Thai | Tai-Kadai | Kam-Tai | Mid |
|
308 |
+
| tur | Turkish | Latin | Turkic | Common Turkic | High |
|
309 |
+
| twi | Twi | Latin | Atlantic-Congo | Niger-Congo | Low |
|
310 |
+
| ukr | Ukrainian | Cyrillic | Indo-European | Balto-Slavic | Mid |
|
311 |
+
| urd | Urdu | Arabic | Indo-European | Indo-Aryan | Mid |
|
312 |
+
| uzb | Uzbek | Latin | Turkic | Common Turkic | Mid |
|
313 |
+
| vie | Vietnamese | Latin | Austroasiatic | Vietic | High |
|
314 |
+
| xho | Xhosa | Latin | Atlantic-Congo | Benue-Congo | Low |
|
315 |
+
| yid | Yiddish | Hebrew | Indo-European | Germanic | Low |
|
316 |
+
| yor | Yoruba | Latin | Atlantic-Congo | Benue-Congo | Low |
|
317 |
+
| zho | Chinese | Han | Sino-Tibetan | Sinitic | High |
|
318 |
+
| zul | Zulu | Latin | Atlantic-Congo | Benue-Congo | Low |
|
319 |
+
</details>
|
320 |
+
|
321 |
+
## Model Card Contact
|
322 |
+
|
323 |
+
For errors in this model card, contact Ahmet or Viraat, `{ahmet, viraat} at cohere dot com`.
|
aya-fig1.png
ADDED
![]() |
Git LFS Details
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/patrick/t5/mt5-xxl",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 10240,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 4096,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"num_decoder_layers": 24,
|
21 |
+
"num_heads": 64,
|
22 |
+
"num_layers": 24,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"tokenizer_class": "T5Tokenizer",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.37.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 250112
|
33 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.37.2"
|
7 |
+
}
|
model-00001-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaac4cc53b7c0738864e726f7976dd2cbff6d167b6cd4e72e15606461604b116
|
3 |
+
size 4936738248
|
model-00002-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b7d9743953efc11370b813d975b4046e2fbaf004fe55fe686409d132f4b178b
|
3 |
+
size 4999830632
|
model-00003-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f8da8e738617a5256dae1da5a6c92c16279367e13175e922308f435faa6d7de
|
3 |
+
size 4966276000
|
model-00004-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcb7390396e45e71f2ca8f0a204f6a50be6f03a5951170f597bf4fca800bdea7
|
3 |
+
size 4899167392
|
model-00005-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2f5a0027f5f1809388e558a3deb006aec6b5dec558e8a0ae33217d1ba06cc37
|
3 |
+
size 4966301192
|
model-00006-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d91b037f502b324a480245cd196832e4e840cf0af44c18cb8e9d7756d423887c
|
3 |
+
size 4966293592
|
model-00007-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69a3500ef0e35b6b289b8fb619f375b4db1290c2ebe4278a11c5b59eb0caab53
|
3 |
+
size 4865646808
|
model-00008-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4021348ceeb4272a002c4005f12e96ed42dc3c6125a202f45948de035ae0a9fb
|
3 |
+
size 4999847960
|
model-00009-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ca4b582de8e0f51bcc7308cc1d28702a51d481161ebd727ebfcd96044640180
|
3 |
+
size 4999847960
|
model-00010-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d700edf476d61769820ea28cdb6fcfb56a549cb688c5bfd52fe35d1ff581a190
|
3 |
+
size 2986513368
|
model-00011-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af58c4bfa00af282c826f2d1322be3ee5c264e976f56808357d37e800a2d7fca
|
3 |
+
size 4097835136
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f98df44db210aa12dbb84ec724d0c25d2dcef709fa73a317b769eeea08a9898
|
3 |
+
size 50639
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87a036c0dfd2d80e1202a7e2961aeee653ff63d67cd369b155c78a6e2003a390
|
3 |
+
size 16330562
|
tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "</s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<unk>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
+
"clean_up_tokenization_spaces": true,
|
30 |
+
"eos_token": "</s>",
|
31 |
+
"extra_ids": 0,
|
32 |
+
"legacy": true,
|
33 |
+
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": "<pad>",
|
35 |
+
"sp_model_kwargs": {},
|
36 |
+
"tokenizer_class": "T5Tokenizer",
|
37 |
+
"unk_token": "<unk>"
|
38 |
+
}
|