remove pytorch ckpt

README.md

@@ -1,42 +0,0 @@
----
-language: ko
-tags:
-  - korean
-mask_token: "[MASK]"
-widget:
-  - text: 대한민국의 수도는 [MASK] 입니다.
----
-
-# KoBigBird
-
-Pretrained BigBird Model for Korean (**kobigbird-bert-base**)
-
-## About
-
-BigBird, is a sparse-attention based transformer which extends Transformer based models, such as BERT to much longer sequences.
-
-BigBird relies on **block sparse attention** instead of normal attention (i.e. BERT's attention) and can handle sequences up to a length of 4096 at a much lower compute cost compared to BERT.
-
-Model is warm started from Korean BERT’s checkpoint.
-
-## How to use
-
-*NOTE:* Use `BertTokenizer` instead of BigBirdTokenizer. (`AutoTokenizer` will load `BertTokenizer`)
-
-```python
-from transformers import AutoModel, AutoTokenizer
-
-# by default its in `block_sparse` mode with num_random_blocks=3, block_size=64
-model = AutoModel.from_pretrained("monologg/kobigbird-bert-base")
-
-# you can change `attention_type` to full attention like this:
-model = AutoModel.from_pretrained("monologg/kobigbird-bert-base", attention_type="original_full")
-
-# you can change `block_size` & `num_random_blocks` like this:
-model = AutoModel.from_pretrained("monologg/kobigbird-bert-base", block_size=16, num_random_blocks=2)
-
-tokenizer = AutoTokenizer.from_pretrained("monologg/kobigbird-bert-base")
-text = "한국어 BigBird 모델을 공개합니다!"
-encoded_input = tokenizer(text, return_tensors='pt')
-output = model(**encoded_input)
-```

config.json

@@ -1,34 +0,0 @@
-{
-  "architectures": [
-    "BigBirdForMaskedLM"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "attention_type": "block_sparse",
-  "block_size": 64,
-  "bos_token_id": 5,
-  "classifier_dropout": null,
-  "eos_token_id": 6,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu_new",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 4096,
-  "model_type": "big_bird",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "num_random_blocks": 3,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "rescale_embeddings": false,
-  "sep_token_id": 3,
-  "tokenizer_class": "BertTokenizer",
-  "torch_dtype": "float32",
-  "transformers_version": "4.11.3",
-  "type_vocab_size": 2,
-  "use_bias": true,
-  "use_cache": true,
-  "vocab_size": 32500
-}

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:34fc7d7536b6c78fa17af2a99bada8684fde89e172dd677b289eea0f83298cd6
-size 457600984

special_tokens_map.json

@@ -1,9 +0,0 @@
-{
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "unk_token": "[UNK]",
-  "sep_token": "[SEP]",
-  "pad_token": "[PAD]",
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]"
-}

tokenizer_config.json

@@ -1,16 +0,0 @@
-{
-  "do_lower_case": false,
-  "unk_token": "[UNK]",
-  "sep_token": "[SEP]",
-  "pad_token": "[PAD]",
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "tokenize_chinese_chars": true,
-  "strip_accents": null,
-  "do_basic_tokenize": true,
-  "never_split": null,
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "model_max_length": 4096,
-  "tokenizer_class": "BertTokenizer"
-}