Added initial versions of the domain-specific legislation model.

* Converted from model.npz file trained with Marian NMT v1.12.0.

* Conversion performed with slightly modified version of
`transformers.models.marian.convert_marian_to_pytorch`.

.gitattributes

@@ -32,3 +32,4 @@ 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
+*.spm filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,44 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      50000
+    ]
+  ],
+  "bos_token_id": 0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 50000,
+  "decoder_vocab_size": 50001,
+  "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,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 50000,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 50001
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      50000
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 50000,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 50000,
+  "transformers_version": "4.26.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd0b700bba31cc03e2816f861c6816cd593a857179a15e0cb4bebb0214f4c6e7
+size 190862153

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ed8cbbf75093a78a9b3c6cb36893e20d87e1fa81bba8c1b11c248f855fe2ca
+size 1145931

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 sha256:29ed8cbbf75093a78a9b3c6cb36893e20d87e1fa81bba8c1b11c248f855fe2ca
+size 1145931

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "special_tokens_map.json",
+  "target_lang": "cy",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}