first commit

README.md

@@ -0,0 +1,51 @@
+---
+tags:
+- translation
+- torch==1.8.0
+widget:
+- text: "Inference Unavailable"
+---
+### marianmt-th-zh_cn
+* source languages: th
+* target languages: zh_cn
+* dataset: 
+* model: transformer-align
+* pre-processing: normalization + SentencePiece
+* test set translations: 
+* test set scores: 
+
+## Training
+
+Training scripts from [LalitaDeelert/NLP-ZH_TH-Project](https://github.com/LalitaDeelert/NLP-ZH_TH-Project). Experiments tracked at [cstorm125/marianmt-th-zh_cn](https://wandb.ai/cstorm125/marianmt-th-zh_cn).
+
+```
+export WANDB_PROJECT=marianmt-th-zh_cn
+python train_model.py --input_fname ../data/v1/Train.csv \
+	--output_dir ../models/marianmt-th-zh_cn \
+	--source_lang th --target_lang zh \
+	--metric_tokenize zh --fp16
+```
+
+## Usage
+
+```
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+ 
+tokenizer = AutoTokenizer.from_pretrained("cstorm125/marianmt-zh_cn-th")
+model = AutoModelForSeq2SeqLM.from_pretrained("cstorm125/marianmt-zh_cn-th").cpu()
+
+src_text = [
+    'ฉันรักคุณ',
+    'ฉันอยากกินข้าว',
+]
+translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
+print([tokenizer.decode(t, skip_special_tokens=True) for t in translated])
+
+> ['我爱你', '我想吃饭。']
+```
+
+## Requirements
+```
+transformers==4.6.0
+torch==1.8.0
+```

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "checkpoint-191340",
+  "_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,
+  "bad_words_ids": [
+    [
+      3
+    ]
+  ],
+  "bos_token_id": 1,
+  "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": 3,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "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": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 3,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.6.0",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 32001
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8823d26bf4238cc9cc1ffb54ae2bcac8cdeb863fcf5daa7bc4edb61e3dc82aeb
+size 242307293

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": null, "target_lang": null, "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "checkpoint-191340"}