Upload kobigbird-bert-base

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "BigBirdForPreTraining"
+  ],
+  "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

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

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "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"
+}