init

README.md

@@ -0,0 +1,14 @@
+---
+language:
+- zh
+license:
+- apache-2.0
+---
+```python
+from transformers import BertTokenizer
+from transformers import BigBirdModel
+
+model = BigBirdModel.from_pretrained('Lowin/chinese-bigbird-base-wwm')
+tokenizer = BertTokenizer.from_pretrained('Lowin/chinese-bigbird-base-wwm')
+```
+https://github.com/LowinLi/chinese-bigbird

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "BigBirdForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "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,
+  "output_past": true,
+  "pad_token_id": 1,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "rescale_embeddings": false,
+  "sep_token_id": 66,
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "type_vocab_size": 2,
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ecdf791554260c45f29152a2b2ebaff9139554237853055e47273089cd94f2
+size 422650980