Translation
Transformers
Safetensors
Chinese
Vietnamese
marian
text2text-generation
chinese-vietnamese
webnovel
xianxia
nmt
machine-translation
asymmetric-transformer
trained-from-scratch
Instructions to use ngocdang83/HachimiMT-60-zh-vi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ngocdang83/HachimiMT-60-zh-vi 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="ngocdang83/HachimiMT-60-zh-vi")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ngocdang83/HachimiMT-60-zh-vi") model = AutoModelForSeq2SeqLM.from_pretrained("ngocdang83/HachimiMT-60-zh-vi", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add CTranslate2 INT8 runtime
Browse files- ct2-int8_float32/config.json +10 -0
- ct2-int8_float32/generation_config.json +12 -0
- ct2-int8_float32/model.bin +3 -0
- ct2-int8_float32/shared_vocabulary.json +0 -0
- ct2-int8_float32/source.spm +3 -0
- ct2-int8_float32/target.spm +3 -0
- ct2-int8_float32/tokenizer_config.json +50 -0
- ct2-int8_float32/vocab.json +0 -0
ct2-int8_float32/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": "<pad>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"layer_norm_epsilon": null,
|
| 8 |
+
"multi_query_attention": false,
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|
ct2-int8_float32/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"decoder_start_token_id": 0,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_eos_token_id": 2,
|
| 7 |
+
"output_attentions": false,
|
| 8 |
+
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"transformers_version": "5.9.0",
|
| 11 |
+
"use_cache": true
|
| 12 |
+
}
|
ct2-int8_float32/model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed9e9ec52051916be15ebedd9aff71bcb7a30300ee8d2fc2ec818670d222a881
|
| 3 |
+
size 58057231
|
ct2-int8_float32/shared_vocabulary.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ct2-int8_float32/source.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1557335c5892d2f33c6a4864f3ae598b235f705a713e32ca020b9fadb99a99e
|
| 3 |
+
size 606202
|
ct2-int8_float32/target.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1557335c5892d2f33c6a4864f3ae598b235f705a713e32ca020b9fadb99a99e
|
| 3 |
+
size 606202
|
ct2-int8_float32/tokenizer_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"backend": "custom",
|
| 37 |
+
"bos_token": "<s>",
|
| 38 |
+
"clean_up_tokenization_spaces": false,
|
| 39 |
+
"eos_token": "</s>",
|
| 40 |
+
"is_local": true,
|
| 41 |
+
"local_files_only": false,
|
| 42 |
+
"model_max_length": 512,
|
| 43 |
+
"pad_token": "<pad>",
|
| 44 |
+
"separate_vocabs": false,
|
| 45 |
+
"source_lang": null,
|
| 46 |
+
"sp_model_kwargs": {},
|
| 47 |
+
"target_lang": null,
|
| 48 |
+
"tokenizer_class": "MarianTokenizer",
|
| 49 |
+
"unk_token": "<unk>"
|
| 50 |
+
}
|
ct2-int8_float32/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|