initial commit

This commit is contained in:
gw.kim 2022-07-19 13:50:39 +00:00
parent 063d2cad99
commit a813850403
6 changed files with 32 additions and 0 deletions

1
added_tokens.json Normal file
View File

@ -0,0 +1 @@
{"<sep/>": 57522, "<s_iitcdip>": 57523, "<s_synthdog>": 57524}

23
config.json Normal file
View File

@ -0,0 +1,23 @@
{
"align_long_axis": true,
"architectures": [
"DonutModel"
],
"decoder_layer": 4,
"encoder_layer": [
2,
2,
14,
2
],
"input_size": [
2560,
1920
],
"max_length": 1536,
"max_position_embeddings": 1536,
"model_type": "donut",
"torch_dtype": "float32",
"transformers_version": "4.11.3",
"window_size": 10
}

3
pytorch_model.bin Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d21e8b5e708168f4f9885d18f8bc95ad6950439e7ac518161828ff0b27b984e8
size 1018458179

BIN
sentencepiece.bpe.model (Stored with Git LFS) Normal file

Binary file not shown.

1
special_tokens_map.json Normal file
View File

@ -0,0 +1 @@
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<s_iitcdip>", "<s_synthdog>"]}

1
tokenizer_config.json Normal file
View File

@ -0,0 +1 @@
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/213c2041358e63047b407f94cde1ae23904d31a3bceb57eab291028c1e949437.7135a4b25ac726e19641f0d68803ff02bad960d6319064f55fa9c536929b86fc", "name_or_path": "hyunwoongko/asian-bart-ecjk", "tokenizer_class": "XLMRobertaTokenizer"}