Phase 1 initial upload: Helsinki-NLP/opus-mt-cpp-cpp → CT2 float16
Browse files- .gitattributes +2 -0
- README.md +36 -0
- config.json +10 -0
- model.bin +3 -0
- shared_vocabulary.json +0 -0
- source.spm +3 -0
- target.spm +3 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* 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
|
|
|
|
|
|
|
|
|
| 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 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- translation
|
| 5 |
+
- opus-mt
|
| 6 |
+
- ctranslate2
|
| 7 |
+
- custom
|
| 8 |
+
source_model: Helsinki-NLP/opus-mt-cpp-cpp
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# ooeoeo/opus-mt-cpp-cpp-ct2-float16
|
| 12 |
+
|
| 13 |
+
CTranslate2 float16 quantized version of `Helsinki-NLP/opus-mt-cpp-cpp`.
|
| 14 |
+
|
| 15 |
+
Converted for use in the [ooeoeo](https://ooeoeo.com) desktop engine
|
| 16 |
+
with the `opus-mt-server` inference runtime.
|
| 17 |
+
|
| 18 |
+
## Source
|
| 19 |
+
|
| 20 |
+
- Upstream model: [Helsinki-NLP/opus-mt-cpp-cpp](https://huggingface.co/Helsinki-NLP/opus-mt-cpp-cpp)
|
| 21 |
+
- Variant: `custom`
|
| 22 |
+
- Language pair: `custom`
|
| 23 |
+
|
| 24 |
+
## Conversion
|
| 25 |
+
|
| 26 |
+
```bash
|
| 27 |
+
ct2-transformers-converter \
|
| 28 |
+
--model Helsinki-NLP/opus-mt-cpp-cpp \
|
| 29 |
+
--output_dir ct2/ \
|
| 30 |
+
--quantization float16 \
|
| 31 |
+
--copy_files source.spm target.spm tokenizer_config.json vocab.json
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
## License
|
| 35 |
+
|
| 36 |
+
Apache-2.0 (inherited from upstream Helsinki-NLP/Opus-MT).
|
config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_source_bos": false,
|
| 3 |
+
"add_source_eos": false,
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"decoder_start_token": "</s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"layer_norm_epsilon": null,
|
| 8 |
+
"multi_query_attention": false,
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|
model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf535e37f268878a4f747a0d8f39904700364c4ff23f777180a4757c4ba6a461
|
| 3 |
+
size 121632303
|
shared_vocabulary.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
source.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0cc6ac66cf8727264edcbbe258acfd3c6b1a9ebc89f0523af41ab7a0570385c
|
| 3 |
+
size 831150
|
target.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d77f1367469313d52b0d39f4ab41fc9cf8ffb90f21802742939265b39c2bf082
|
| 3 |
+
size 831150
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"target_lang": "cpp", "source_lang": "cpp"}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|