Upload folder using huggingface_hub

.gitattributes

@@ -1,34 +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
 *.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

README.md

@@ -0,0 +1,75 @@
+---
+tags:
+- ctranslate2
+- translation
+license: apache-2.0
+---
+# # Fast-Inference with Ctranslate2
+Speedup inference by 2x-8x using int8 inference in C++
+
+quantized version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr)
+```bash
+pip install hf-hub-ctranslate2>=1.0.0 ctranslate2>=3.13.0
+```
+Converted using
+```
+ct2-transformers-converter --model Helsinki-NLP/opus-mt-en-fr --output_dir /home/michael/tmp-ct2fast-opus-mt-en-fr --force --copy_files README.md generation_config.json tokenizer_config.json vocab.json source.spm .gitattributes target.spm --quantization float16
+```
+
+Checkpoint compatible to [ctranslate2](https://github.com/OpenNMT/CTranslate2) and [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2)
+- `compute_type=int8_float16` for `device="cuda"` 
+- `compute_type=int8`  for `device="cpu"`
+
+```python
+from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
+from transformers import AutoTokenizer
+
+model_name = "michaelfeil/ct2fast-opus-mt-en-fr"
+# use either TranslatorCT2fromHfHub or GeneratorCT2fromHfHub here, depending on model.
+model = TranslatorCT2fromHfHub(
+        # load in int8 on CUDA
+        model_name_or_path=model_name, 
+        device="cuda",
+        compute_type="int8_float16",
+        tokenizer=AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-fr")
+)
+outputs = model.generate(
+    text=["How do you call a fast Flan-ingo?", "User: How are you doing?"],
+)
+print(outputs)
+```
+
+# Licence and other remarks:
+This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.
+
+# Original description
+    
+
+### opus-mt-en-fr
+
+* source languages: en
+* target languages: fr
+*  OPUS readme: [en-fr](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-fr/README.md)
+
+*  dataset: opus
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* download original weights: [opus-2020-02-26.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-fr/opus-2020-02-26.zip)
+* test set translations: [opus-2020-02-26.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-fr/opus-2020-02-26.test.txt)
+* test set scores: [opus-2020-02-26.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-fr/opus-2020-02-26.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| newsdiscussdev2015-enfr.en.fr 	| 33.8 	| 0.602 |
+| newsdiscusstest2015-enfr.en.fr 	| 40.0 	| 0.643 |
+| newssyscomb2009.en.fr 	| 29.8 	| 0.584 |
+| news-test2008.en.fr 	| 27.5 	| 0.554 |
+| newstest2009.en.fr 	| 29.4 	| 0.577 |
+| newstest2010.en.fr 	| 32.7 	| 0.596 |
+| newstest2011.en.fr 	| 34.3 	| 0.611 |
+| newstest2012.en.fr 	| 31.8 	| 0.592 |
+| newstest2013.en.fr 	| 33.2 	| 0.589 |
+| Tatoeba.en.fr 	| 50.5 	| 0.672 |
+

config.json

@@ -0,0 +1,8 @@
+{
+  "add_source_bos": false,
+  "add_source_eos": false,
+  "bos_token": "<s>",
+  "decoder_start_token": "</s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 59513,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59513,
+  "transformers_version": "4.27.0.dev0"
+}

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:636d926880a6e6e4b773403a5991b50d4dfdfabe49a230e148676a05e99f2bec
+size 149872839

tokenizer_config.json

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