Upload folder using huggingface_hub

.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 +1,34 @@
+---
+library_name: transformers.js
+tags:
+- translation
+- onnx
+- marian
+- opus-mt
+---
+
+# Devsyril/opus-mt-en-ee-onnx
+
+Export ONNX du modèle [`Helsinki-NLP/opus-mt-en-ee`](https://huggingface.co/Helsinki-NLP/opus-mt-en-ee) (Helsinki-NLP / OPUS-MT),
+généré avec [🤗 Optimum](https://github.com/huggingface/optimum).
+
+Contient les composants ONNX standards pour un modèle seq2seq :
+`encoder_model.onnx`, `decoder_model.onnx`, `decoder_with_past_model.onnx` (selon la version d'Optimum utilisée),
+ainsi que le tokenizer d'origine.
+
+## Utilisation
+
+```python
+from optimum.onnxruntime import ORTModelForSeq2SeqLM
+from transformers import AutoTokenizer
+
+repo_id = "Devsyril/opus-mt-en-ee-onnx"
+model = ORTModelForSeq2SeqLM.from_pretrained(repo_id)
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+
+inputs = tokenizer("Ton texte ici", return_tensors="pt")
+generated = model.generate(**inputs)
+print(tokenizer.batch_decode(generated, skip_special_tokens=True))
+```
+
+Modèle source : Helsinki-NLP/opus-mt-en-ee

config.json

@@ -0,0 +1,54 @@
+{
+  "_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,
+  "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": 57578,
+  "decoder_vocab_size": 57579,
+  "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,
+  "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": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 57578,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 57579
+}

decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167dd4dca2641541f557d9300c7136a0d97b707952abed48293d2b5a6cbba10c
+size 338220561

decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322b827a9b2f3dabadaafe96ea6f6ca500a42ec71377cfe7b2cb12fa1f3a93c3
+size 325590954

encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef8782b2edc89e88c7180cfc61b6fec996c459d0a7b902d28ab23c7f58d4080
+size 194701942

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      57578
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 57578,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 57578,
+  "renormalize_logits": true,
+  "transformers_version": "4.57.6"
+}

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f183389c6fab3df8a90239b92146f07f595241c40c7fa034cf5a0bc4d78cca29
+size 823630

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66f6affa60cd6f5fb9f23277efeeb232b8d0839e5f11e9352f343a6a7dc6085
+size 831343

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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
+    },
+    "57578": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "ee",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}