Upload 10 files

.gitattributes

@@ -1,35 +1,32 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,66 @@
+---
+language:
+- vi
+- en
+datasets:
+- cc100
+tags:
+- translation
+
+widget:
+- text: "vi: VietAI là tổ chức phi lợi nhuận với sứ mệnh ươm mầm tài năng về trí tuệ nhân tạo và xây dựng một cộng đồng các chuyên gia trong lĩnh vực trí tuệ nhân tạo đẳng cấp quốc tế tại Việt Nam."
+
+license: openrail
+---
+
+# EnViT5 Translation
+
+[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mtet-multi-domain-translation-for-english/machine-translation-on-iwslt2015-english-1)](https://paperswithcode.com/sota/machine-translation-on-iwslt2015-english-1?p=mtet-multi-domain-translation-for-english)
+
+[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mtet-multi-domain-translation-for-english-and/on-phomt)](https://paperswithcode.com/sota/on-phomt?p=mtet-multi-domain-translation-for-english-and)
+
+
+State-of-the-art English-Vietnamese and Vietnamese-English Translation models trained on [MTet](https://research.vietai.org/mtet/), [PhoMT](https://github.com/VinAIResearch/PhoMT).
+
+
+
+
+```python
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+
+model_name = "VietAI/envit5-translation"
+tokenizer = AutoTokenizer.from_pretrained(model_name)  
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+inputs = [
+    "vi: VietAI là tổ chức phi lợi nhuận với sứ mệnh ươm mầm tài năng về trí tuệ nhân tạo và xây dựng một cộng đồng các chuyên gia trong lĩnh vực trí tuệ nhân tạo đẳng cấp quốc tế tại Việt Nam.",
+    "vi: Theo báo cáo mới nhất của Linkedin về danh sách việc làm triển vọng với mức lương hấp dẫn năm 2020, các chức danh công việc liên quan đến AI như Chuyên gia AI (Artificial Intelligence Specialist), Kỹ sư ML (Machine Learning Engineer) đều xếp thứ hạng cao.",
+    "en: Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.",
+    "en: We're on a journey to advance and democratize artificial intelligence through open source and open science."
+    ]
+
+outputs = model.generate(tokenizer(inputs, return_tensors="pt", padding=True).input_ids.to('cuda'), max_length=512)
+print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
+
+# ['en: VietAI is a non-profit organization with the mission of nurturing artificial intelligence talents and building an international - class community of artificial intelligence experts in Vietnam.',
+#  'en: According to the latest LinkedIn report on the 2020 list of attractive and promising jobs, AI - related job titles such as AI Specialist, ML Engineer and ML Engineer all rank high.',
+#  'vi: Nhóm chúng tôi khao khát tạo ra những khám phá có ảnh hưởng đến mọi người, và cốt lõi trong cách tiếp cận của chúng tôi là chia sẻ nghiên cứu và công cụ để thúc đẩy sự tiến bộ trong lĩnh vực này.',
+#  'vi: Chúng ta đang trên hành trình tiến bộ và dân chủ hoá trí tuệ nhân tạo thông qua mã nguồn mở và khoa học mở.']
+
+```
+
+## Results
+
+![image](https://user-images.githubusercontent.com/44376091/195998681-5860e443-2071-4048-8a2b-873dcee14a72.png)
+
+## Citation
+```
+@misc{https://doi.org/10.48550/arxiv.2210.05610,
+  doi = {10.48550/ARXIV.2210.05610},
+  author = {Ngo, Chinh and Trinh, Trieu H. and Phan, Long and Tran, Hieu and Dang, Tai and Nguyen, Hieu and Nguyen, Minh and Luong, Minh-Thang},
+  title = {MTet: Multi-domain Translation for English and Vietnamese},
+  publisher = {arXiv},
+  year = {2022},
+}
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.2",
+  "use_cache": true,
+  "vocab_size": 50048
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d170ffff27d6b3bcccfb069049326483ffcdc706a42eead8b1d6a4686b3492c4
+size 1100424095

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef48b3eee23aae577e965ce8da5b2e9dcadfc4d08a85e2a302ef4b929fb613e
+size 1100503117

special_tokens_map.json

@@ -0,0 +1,55 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4eda923bbac1726e8fda66254a8783ecc705be5577149ee8c98074efdb5de5
+size 1102207

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6870be5fa2ebd227b14e93b4cc904e9d9548a0d95f79483f37ad0f5856f0d5e
+size 1100986512

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 48,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}