cointegrated
commited on
Commit
•
676efa5
1
Parent(s):
d3afeb2
Update README.md
Browse files
README.md
CHANGED
@@ -1,199 +1,126 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
-
# Model Card for
|
7 |
-
|
8 |
-
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
|
|
|
|
|
|
|
|
|
10 |
|
11 |
|
12 |
## Model Details
|
13 |
|
14 |
### Model Description
|
15 |
|
16 |
-
<!-- Provide a longer summary of what this model is. -->
|
17 |
-
|
18 |
-
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
19 |
|
20 |
-
- **Developed by:**
|
21 |
-
- **
|
22 |
-
- **
|
23 |
-
- **
|
24 |
-
- **
|
25 |
-
- **License:** [More Information Needed]
|
26 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
|
28 |
### Model Sources [optional]
|
29 |
|
30 |
<!-- Provide the basic links for the model. -->
|
31 |
|
32 |
-
- **Repository:**
|
33 |
-
- **Paper
|
34 |
-
- **Demo
|
35 |
|
36 |
## Uses
|
37 |
|
38 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
-
|
40 |
### Direct Use
|
41 |
-
|
42 |
-
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
-
|
44 |
-
[More Information Needed]
|
45 |
-
|
46 |
-
### Downstream Use [optional]
|
47 |
-
|
48 |
-
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
-
|
50 |
-
[More Information Needed]
|
51 |
|
52 |
### Out-of-Scope Use
|
53 |
-
|
54 |
-
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
-
|
56 |
-
[More Information Needed]
|
57 |
|
58 |
## Bias, Risks, and Limitations
|
|
|
59 |
|
60 |
-
|
61 |
-
|
62 |
-
[More Information Needed]
|
63 |
|
64 |
### Recommendations
|
65 |
-
|
66 |
-
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
-
|
68 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
|
70 |
## How to Get Started with the Model
|
71 |
|
72 |
-
|
73 |
-
|
74 |
-
[More Information Needed]
|
75 |
|
76 |
## Training Details
|
77 |
|
78 |
### Training Data
|
79 |
|
80 |
-
|
81 |
-
|
82 |
-
[More Information Needed]
|
83 |
|
84 |
### Training Procedure
|
85 |
|
86 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
|
88 |
#### Preprocessing [optional]
|
89 |
|
90 |
-
|
|
|
91 |
|
|
|
92 |
|
93 |
#### Training Hyperparameters
|
94 |
|
95 |
-
|
96 |
-
|
97 |
-
#### Speeds, Sizes, Times [optional]
|
98 |
-
|
99 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
-
|
101 |
-
[More Information Needed]
|
102 |
-
|
103 |
-
## Evaluation
|
104 |
-
|
105 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
-
|
107 |
-
### Testing Data, Factors & Metrics
|
108 |
-
|
109 |
-
#### Testing Data
|
110 |
-
|
111 |
-
<!-- This should link to a Dataset Card if possible. -->
|
112 |
-
|
113 |
-
[More Information Needed]
|
114 |
-
|
115 |
-
#### Factors
|
116 |
-
|
117 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
-
|
119 |
-
[More Information Needed]
|
120 |
-
|
121 |
-
#### Metrics
|
122 |
|
123 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
124 |
|
125 |
-
[More Information Needed]
|
126 |
|
127 |
-
|
128 |
-
|
129 |
-
[More Information Needed]
|
130 |
-
|
131 |
-
#### Summary
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
## Model Examination [optional]
|
136 |
-
|
137 |
-
<!-- Relevant interpretability work for the model goes here -->
|
138 |
-
|
139 |
-
[More Information Needed]
|
140 |
-
|
141 |
-
## Environmental Impact
|
142 |
-
|
143 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
-
|
145 |
-
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
-
|
147 |
-
- **Hardware Type:** [More Information Needed]
|
148 |
-
- **Hours used:** [More Information Needed]
|
149 |
-
- **Cloud Provider:** [More Information Needed]
|
150 |
-
- **Compute Region:** [More Information Needed]
|
151 |
-
- **Carbon Emitted:** [More Information Needed]
|
152 |
-
|
153 |
-
## Technical Specifications [optional]
|
154 |
|
155 |
### Model Architecture and Objective
|
156 |
|
157 |
-
|
158 |
|
159 |
### Compute Infrastructure
|
160 |
|
161 |
-
|
162 |
-
|
163 |
-
#### Hardware
|
164 |
-
|
165 |
-
[More Information Needed]
|
166 |
-
|
167 |
-
#### Software
|
168 |
-
|
169 |
-
[More Information Needed]
|
170 |
-
|
171 |
-
## Citation [optional]
|
172 |
-
|
173 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
-
|
175 |
-
**BibTeX:**
|
176 |
-
|
177 |
-
[More Information Needed]
|
178 |
-
|
179 |
-
**APA:**
|
180 |
-
|
181 |
-
[More Information Needed]
|
182 |
-
|
183 |
-
## Glossary [optional]
|
184 |
-
|
185 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
-
|
187 |
-
[More Information Needed]
|
188 |
-
|
189 |
-
## More Information [optional]
|
190 |
-
|
191 |
-
[More Information Needed]
|
192 |
-
|
193 |
-
## Model Card Authors [optional]
|
194 |
|
195 |
-
|
|
|
|
|
196 |
|
197 |
## Model Card Contact
|
198 |
|
199 |
-
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
license: cc-by-nc-4.0
|
4 |
+
language:
|
5 |
+
- myv
|
6 |
+
- ru
|
7 |
+
- ar
|
8 |
+
- en
|
9 |
+
- et
|
10 |
+
- fr
|
11 |
+
- de
|
12 |
+
- kk
|
13 |
+
- ch
|
14 |
+
- zh
|
15 |
+
- mn
|
16 |
+
- es
|
17 |
+
- tr
|
18 |
+
- uk
|
19 |
+
- uz
|
20 |
+
base_model:
|
21 |
+
- facebook/nllb-200-distilled-600M
|
22 |
+
datasets:
|
23 |
+
- slone/myv_ru_2022
|
24 |
+
- slone/e-mordovia-articles-2023
|
25 |
+
pipeline_tag: translation
|
26 |
---
|
27 |
|
28 |
+
# Model Card for NLLB-with-myv-v2024 (a translation model for Erzya)
|
|
|
|
|
29 |
|
30 |
+
This is a version of the [nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) machine translation model
|
31 |
+
with one added language: Erzya (the new language code is `myv_Cyrl`).
|
32 |
+
It can probably translate from all 202 NLLB languages, but it fine-tuned with the focus on Erzya, Russian, and, to a lesser extent,
|
33 |
+
on Arabic, English, Estonian, Finnish, French, German, Kazakh, Mandarin, Mongolian, Spanish, Turkish, Ukrainian, and Uzbek.
|
34 |
|
35 |
|
36 |
## Model Details
|
37 |
|
38 |
### Model Description
|
39 |
|
|
|
|
|
|
|
40 |
|
41 |
+
- **Developed by:** Isai Gordeev, Sergey Kuldin and David Dale
|
42 |
+
- **Model type:** Encoder-decoder transformer
|
43 |
+
- **Language(s) (NLP):** Erzya, Russian, and all the 202 NLLB languages.
|
44 |
+
- **License:** CC-BY-NC-4.0
|
45 |
+
- **Finetuned from model:** [nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M)
|
|
|
|
|
46 |
|
47 |
### Model Sources [optional]
|
48 |
|
49 |
<!-- Provide the basic links for the model. -->
|
50 |
|
51 |
+
- **Repository:** will be published later
|
52 |
+
- **Paper:** will be published later
|
53 |
+
- **Demo:** https://lango.to/ (it is powered by a similar model)
|
54 |
|
55 |
## Uses
|
56 |
|
|
|
|
|
57 |
### Direct Use
|
58 |
+
Translation between Erzya, Russian, and potentially other languages. The model seems to be SOTA for translating into Erzya.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
|
60 |
### Out-of-Scope Use
|
61 |
+
Translation between other NLLB languages, not inclusing Erzya as source or target.
|
|
|
|
|
|
|
62 |
|
63 |
## Bias, Risks, and Limitations
|
64 |
+
The model is not producing the most fluent translations into Russian and other high-resourced languages.
|
65 |
|
66 |
+
Its translations into Erzya seem to be better than anything else, but may still include inaccurate or ungrammatical translations,
|
67 |
+
so they should be always manually reviewed before any high-responsibility use.
|
|
|
68 |
|
69 |
### Recommendations
|
70 |
+
Please contact the authors for any substantial recommendation.
|
|
|
|
|
|
|
71 |
|
72 |
## How to Get Started with the Model
|
73 |
|
74 |
+
See the NLLB generation code: https://huggingface.co/docs/transformers/v4.44.2/en/model_doc/nllb#generating-with-nllb.
|
|
|
|
|
75 |
|
76 |
## Training Details
|
77 |
|
78 |
### Training Data
|
79 |
|
80 |
+
- https://huggingface.co/datasets/slone/myv_ru_2022
|
81 |
+
- https://huggingface.co/datasets/slone/e-mordovia-articles-2023
|
|
|
82 |
|
83 |
### Training Procedure
|
84 |
|
|
|
85 |
|
86 |
#### Preprocessing [optional]
|
87 |
|
88 |
+
The preprocessing code is adapted from the Stopes repo of the NLLB team:
|
89 |
+
https://github.com/facebookresearch/stopes/blob/main/stopes/pipelines/monolingual/monolingual_line_processor.py#L214
|
90 |
|
91 |
+
It performs punctuation normalization, nonprintable character removal and Unicode normalization.
|
92 |
|
93 |
#### Training Hyperparameters
|
94 |
|
95 |
+
The tokenizer of the model was updated with 6209 new Erzya tokens. They were initialized with the average embeddings of the old tokens from which they are combined.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
96 |
|
97 |
+
- training regime: `fp32`
|
98 |
+
- batch_size: 6
|
99 |
+
- grad_acc_steps: 4
|
100 |
+
- max_length: 128
|
101 |
+
- optimizer: Adafactor
|
102 |
+
- lr: 1e-4
|
103 |
+
- clip_threshold=1.0
|
104 |
+
- weight_decay: 1e-3
|
105 |
+
- warmup_steps: 3_000 (with a linear warmup from 0)
|
106 |
+
- training_steps: 220_000
|
107 |
+
- weight_loss_coef: 100 (a coefficient for the additional penalty, MSE between the embeddings of old tokens and their values for NLLB-200)
|
108 |
|
|
|
109 |
|
110 |
+
## Technical Specifications
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
111 |
|
112 |
### Model Architecture and Objective
|
113 |
|
114 |
+
A standard encoder-decoder translation model with cross-entropy loss.
|
115 |
|
116 |
### Compute Infrastructure
|
117 |
|
118 |
+
Google Colab with a T4 GPU.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
119 |
|
120 |
+
```
|
121 |
+
pip install --upgrade sentencepiece transformers==4.40 datasets sacremoses editdistance sacrebleu razdel ctranslate2
|
122 |
+
```
|
123 |
|
124 |
## Model Card Contact
|
125 |
|
126 |
+
@cointegrated
|