Phase 1 initial upload: Helsinki-NLP/opus-mt-caenes-eo → CT2 float16

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* 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
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,36 @@
+---
+license: apache-2.0
+tags:
+- translation
+- opus-mt
+- ctranslate2
+- custom
+source_model: Helsinki-NLP/opus-mt-caenes-eo
+---
+
+# ooeoeo/opus-mt-caenes-eo-ct2-float16
+
+CTranslate2 float16 quantized version of `Helsinki-NLP/opus-mt-caenes-eo`.
+
+Converted for use in the [ooeoeo](https://ooeoeo.com) desktop engine
+with the `opus-mt-server` inference runtime.
+
+## Source
+
+- Upstream model: [Helsinki-NLP/opus-mt-caenes-eo](https://huggingface.co/Helsinki-NLP/opus-mt-caenes-eo)
+- Variant: `custom`
+- Language pair: `custom`
+
+## Conversion
+
+```bash
+ct2-transformers-converter \
+    --model Helsinki-NLP/opus-mt-caenes-eo \
+    --output_dir ct2/ \
+    --quantization float16 \
+    --copy_files source.spm target.spm tokenizer_config.json vocab.json
+```
+
+## License
+
+Apache-2.0 (inherited from upstream Helsinki-NLP/Opus-MT).

config.json

@@ -0,0 +1,10 @@
+{
+  "add_source_bos": false,
+  "add_source_eos": false,
+  "bos_token": "<s>",
+  "decoder_start_token": "</s>",
+  "eos_token": "</s>",
+  "layer_norm_epsilon": null,
+  "multi_query_attention": false,
+  "unk_token": "<unk>"
+}

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb0aeb968ffa25355c2cf40a300ca0b94d622a405c0fc8a2efe434652922595
+size 121644615

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d561cdf0fc7ad693c1bf1fe21732c6434650623ec69dc712aceb36483587914d
+size 805644

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d561cdf0fc7ad693c1bf1fe21732c6434650623ec69dc712aceb36483587914d
+size 805644

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": null,
+  "sp_model_kwargs": {},
+  "target_lang": null,
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}