upstream-archive byte-perfect snapshot of Helsinki-NLP/opus-mt-en-de (ADR-039 Phase D)

.gitattributes

@@ -1,35 +1,11 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,109 @@
+---
+tags:
+- translation
+license: cc-by-4.0
+---
+
+### opus-mt-en-de
+
+
+## Table of Contents
+- [Model Details](#model-details)
+- [Uses](#uses)
+- [Risks, Limitations and Biases](#risks-limitations-and-biases)
+- [Training](#training)
+- [Evaluation](#evaluation)
+- [Citation Information](#citation-information)
+- [How to Get Started With the Model](#how-to-get-started-with-the-model)
+
+## Model Details
+**Model Description:**
+- **Developed by:** Language Technology Research Group at the University of Helsinki
+- **Model Type:** Translation
+- **Language(s):**  
+  - Source Language: English
+  - Target Language: German 
+- **License:** CC-BY-4.0
+- **Resources for more information:**
+  - [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
+  
+
+## Uses
+
+#### Direct Use
+
+This model can be used for translation and text-to-text generation.
+
+
+## Risks, Limitations and Biases
+
+
+
+**CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes.**
+
+Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
+
+Further details about the dataset for this model can be found in the OPUS readme: [en-de](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-de/README.md)
+
+
+#### Training Data
+##### Preprocessing
+* pre-processing: normalization + SentencePiece
+
+* dataset: [opus](https://github.com/Helsinki-NLP/Opus-MT)
+* download original weights: [opus-2020-02-26.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-de/opus-2020-02-26.zip)
+
+* test set translations: [opus-2020-02-26.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-de/opus-2020-02-26.test.txt)
+
+## Evaluation
+
+#### Results
+
+* test set scores: [opus-2020-02-26.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-de/opus-2020-02-26.eval.txt)
+
+
+#### Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| newssyscomb2009.en.de 	| 23.5 	| 0.540 |
+| news-test2008.en.de 	| 23.5 	| 0.529 |
+| newstest2009.en.de 	| 22.3 	| 0.530 |
+| newstest2010.en.de 	| 24.9 	| 0.544 |
+| newstest2011.en.de 	| 22.5 	| 0.524 |
+| newstest2012.en.de 	| 23.0 	| 0.525 |
+| newstest2013.en.de 	| 26.9 	| 0.553 |
+| newstest2015-ende.en.de 	| 31.1 	| 0.594 |
+| newstest2016-ende.en.de 	| 37.0 	| 0.636 |
+| newstest2017-ende.en.de 	| 29.9 	| 0.586 |
+| newstest2018-ende.en.de 	| 45.2 	| 0.690 |
+| newstest2019-ende.en.de 	| 40.9 	| 0.654 |
+| Tatoeba.en.de 	| 47.3 	| 0.664 |
+
+
+
+## Citation Information
+
+```bibtex
+@InProceedings{TiedemannThottingal:EAMT2020,
+  author = {J{\"o}rg Tiedemann and Santhosh Thottingal},
+  title = {{OPUS-MT} — {B}uilding open translation services for the {W}orld},
+  booktitle = {Proceedings of the 22nd Annual Conferenec of the European Association for Machine Translation (EAMT)},
+  year = {2020},
+  address = {Lisbon, Portugal}
+ }
+```
+
+## How to Get Started With the Model
+```python
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-de")
+
+model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-de")
+
+```
+
+
+
+

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-de",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      58100
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 58100,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 58100,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.9.0.dev0",
+  "use_cache": true,
+  "vocab_size": 58101
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fcf707093bb204211b4e7f8b487896fc65623fd290565992b2105f759539520
+size 295786174

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      58100
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 58100,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 58100,
+  "renormalize_logits": true,
+  "transformers_version": "4.32.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da068344b1b0c20e6d4a8f77f48e06646b90d679029006b18579e68977206bdd
+size 297928209

rust_model.ot

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ab05f28a060d0e72f3d530dfcc5ce972d63e6268bcc87c4affbfd63a137915
+size 535918988

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:678f2a1177d8389f67b66299762dcc4fc567e89b07e212ba91b0c56daecf47ce
+size 768489

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd1f495eea99c8e21ae086d9146e0fa7b096c3dfdd9ba07ab8b631889df5c9b
+size 796845

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2871ccde1f8c20501b0285dd97d757c5c3ad35291bf8711913501f7fdd90ec20
+size 298394200

tokenizer_config.json

@@ -0,0 +1 @@
+{"target_lang": "de", "source_lang": "en"}