Translation
Transformers
Safetensors
marian
windyword
afro-asiatic
arabic
hebrew
amharic
berber
french-italian-portuguese-spanish
french
italian
portuguese
spanish
Instructions to use WindyWord/translate-tcbig-bible_afa-fra_ita_por_spa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WindyWord/translate-tcbig-bible_afa-fra_ita_por_spa with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="WindyWord/translate-tcbig-bible_afa-fra_ita_por_spa")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WindyWord/translate-tcbig-bible_afa-fra_ita_por_spa", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add lora variant
Browse files- .gitattributes +2 -0
- lora/config.json +41 -0
- lora/generation_config.json +16 -0
- lora/model.safetensors +3 -0
- lora/source.spm +3 -0
- lora/special_tokens_map.json +5 -0
- lora/target.spm +3 -0
- lora/tokenizer_config.json +38 -0
- lora/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 |
+
lora/source.spm filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
lora/target.spm filter=lfs diff=lfs merge=lfs -text
|
lora/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-tc-bible-big-afa-fra_ita_por_spa",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "relu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"MarianMTModel"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"d_model": 1024,
|
| 12 |
+
"decoder_attention_heads": 16,
|
| 13 |
+
"decoder_ffn_dim": 4096,
|
| 14 |
+
"decoder_layerdrop": 0.0,
|
| 15 |
+
"decoder_layers": 6,
|
| 16 |
+
"decoder_start_token_id": 61870,
|
| 17 |
+
"decoder_vocab_size": 61871,
|
| 18 |
+
"dropout": 0.1,
|
| 19 |
+
"encoder_attention_heads": 16,
|
| 20 |
+
"encoder_ffn_dim": 4096,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 6,
|
| 23 |
+
"eos_token_id": 331,
|
| 24 |
+
"forced_eos_token_id": null,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"max_length": null,
|
| 28 |
+
"max_position_embeddings": 1024,
|
| 29 |
+
"model_type": "marian",
|
| 30 |
+
"normalize_embedding": false,
|
| 31 |
+
"num_beams": null,
|
| 32 |
+
"num_hidden_layers": 6,
|
| 33 |
+
"pad_token_id": 61870,
|
| 34 |
+
"scale_embedding": true,
|
| 35 |
+
"share_encoder_decoder_embeddings": true,
|
| 36 |
+
"static_position_embeddings": true,
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.45.1",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 61871
|
| 41 |
+
}
|
lora/generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bad_words_ids": [
|
| 4 |
+
[
|
| 5 |
+
61870
|
| 6 |
+
]
|
| 7 |
+
],
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"decoder_start_token_id": 61870,
|
| 10 |
+
"eos_token_id": 331,
|
| 11 |
+
"forced_eos_token_id": 331,
|
| 12 |
+
"max_length": 512,
|
| 13 |
+
"num_beams": 4,
|
| 14 |
+
"pad_token_id": 61870,
|
| 15 |
+
"transformers_version": "4.45.1"
|
| 16 |
+
}
|
lora/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fc64c0d85117f47b64c3d24704bf589626a71e2a66eae3ca86fb3d66a781dcb
|
| 3 |
+
size 959130220
|
lora/source.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b672a33f6c98f8c94b81a720bb8541eee25154c256c4a26ac9cbe6f82d840cb8
|
| 3 |
+
size 822390
|
lora/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
lora/target.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac67981ec12816b6aee6952b3857436ca10e6b90f0e6283e51ac77bc3f988792
|
| 3 |
+
size 817329
|
lora/tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"331": {
|
| 4 |
+
"content": "</s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"589": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"61870": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"clean_up_tokenization_spaces": false,
|
| 29 |
+
"eos_token": "</s>",
|
| 30 |
+
"model_max_length": 512,
|
| 31 |
+
"pad_token": "<pad>",
|
| 32 |
+
"separate_vocabs": false,
|
| 33 |
+
"source_lang": "afa",
|
| 34 |
+
"sp_model_kwargs": {},
|
| 35 |
+
"target_lang": "fra+ita+por+spa",
|
| 36 |
+
"tokenizer_class": "MarianTokenizer",
|
| 37 |
+
"unk_token": "<unk>"
|
| 38 |
+
}
|
lora/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|