Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,9 @@
-*.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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,109 @@
+---
+language: 
+- en
+- de
+tags:
+- translation
+- wmt19
+- facebook
+license: apache-2.0
+datasets:
+- wmt19
+metrics:
+- bleu
+thumbnail: https://huggingface.co/front/thumbnails/facebook.png
+---
+
+# FSMT
+
+## Model description
+
+This is a ported version of [fairseq wmt19 transformer](https://github.com/pytorch/fairseq/blob/master/examples/wmt19/README.md) for en-de.
+
+For more details, please see, [Facebook FAIR's WMT19 News Translation Task Submission](https://arxiv.org/abs/1907.06616).
+
+The abbreviation FSMT stands for FairSeqMachineTranslation
+
+All four models are available:
+
+* [wmt19-en-ru](https://huggingface.co/facebook/wmt19-en-ru)
+* [wmt19-ru-en](https://huggingface.co/facebook/wmt19-ru-en)
+* [wmt19-en-de](https://huggingface.co/facebook/wmt19-en-de)
+* [wmt19-de-en](https://huggingface.co/facebook/wmt19-de-en)
+
+## Intended uses & limitations
+
+#### How to use
+
+```python
+from transformers import FSMTForConditionalGeneration, FSMTTokenizer
+mname = "facebook/wmt19-en-de"
+tokenizer = FSMTTokenizer.from_pretrained(mname)
+model = FSMTForConditionalGeneration.from_pretrained(mname)
+
+input = "Machine learning is great, isn't it?"
+input_ids = tokenizer.encode(input, return_tensors="pt")
+outputs = model.generate(input_ids)
+decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(decoded) # Maschinelles Lernen ist großartig, oder?
+
+```
+
+#### Limitations and bias
+
+- The original (and this ported model) doesn't seem to handle well inputs with repeated sub-phrases, [content gets truncated](https://discuss.huggingface.co/t/issues-with-translating-inputs-containing-repeated-phrases/981)
+
+## Training data
+
+Pretrained weights were left identical to the original model released by fairseq. For more details, please, see the [paper](https://arxiv.org/abs/1907.06616).
+
+## Eval results
+
+pair   | fairseq | transformers
+-------|---------|----------
+en-de  | [43.1](http://matrix.statmt.org/matrix/output/1909?run_id=6862) | 42.83
+
+The score is slightly below the score reported by `fairseq`, since `transformers`` currently doesn't support:
+- model ensemble, therefore the best performing checkpoint was ported (``model4.pt``).
+- re-ranking
+
+The score was calculated using this code:
+
+```bash
+git clone https://github.com/huggingface/transformers
+cd transformers
+export PAIR=en-de
+export DATA_DIR=data/$PAIR
+export SAVE_DIR=data/$PAIR
+export BS=8
+export NUM_BEAMS=15
+mkdir -p $DATA_DIR
+sacrebleu -t wmt19 -l $PAIR --echo src > $DATA_DIR/val.source
+sacrebleu -t wmt19 -l $PAIR --echo ref > $DATA_DIR/val.target
+echo $PAIR
+PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py facebook/wmt19-$PAIR $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS
+```
+note: fairseq reports using a beam of 50, so you should get a slightly higher score if re-run with `--num_beams 50`.
+
+## Data Sources
+
+- [training, etc.](http://www.statmt.org/wmt19/)
+- [test set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
+
+
+### BibTeX entry and citation info
+
+```bibtex
+@inproceedings{...,
+  year={2020},
+  title={Facebook FAIR's WMT19 News Translation Task Submission},
+  author={Ng, Nathan and Yee, Kyra and Baevski, Alexei and Ott, Myle and Auli, Michael and Edunov, Sergey},
+  booktitle={Proc. of WMT},
+}
+```
+
+
+## TODO
+
+- port model ensemble (fairseq uses 4 model checkpoints)
+

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "FSMTForConditionalGeneration"
+  ],
+  "model_type": "fsmt",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "attention_dropout": 0.1,
+  "d_model": 1024,
+  "dropout": 0.2,
+  "init_std": 0.02,
+  "max_position_embeddings": 1024,
+  "num_hidden_layers": 6,
+  "src_vocab_size": 42024,
+  "tgt_vocab_size": 42024,
+  "langs": [
+    "en",
+    "de"
+  ],
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 8192,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 6,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 6,
+  "bos_token_id": 0,
+  "pad_token_id": 1,
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "scale_embedding": true,
+  "tie_word_embeddings": true,
+  "num_beams": 5,
+  "early_stopping": false,
+  "length_penalty": 1.0
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 200,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.27.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7aaf73b048c34ac68ec1622b8f3f053425eecdc64c2d224713342b900f6e0d3
+size 1079014272

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9976b462c4c42afd89e718f44639de30167fdb059fe2b3ad603579eaab73d66c
+size 1079071572

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "langs": [
+    "en",
+    "de"
+  ],
+  "model_max_length": 1024
+}