init model

.gitattributes

@@ -0,0 +1,17 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,55 @@
+---
+
+language:
+
+- zh
+
+license:
+
+- apache-2.0
+
+---
+
+```python
+
+import jieba_fast
+
+from transformers import BertTokenizer
+
+from transformers import BigBirdModel
+
+class JiebaTokenizer(BertTokenizer):
+
+    def __init__(
+
+        self, pre_tokenizer=lambda x: jieba_fast.cut(x, HMM=False), *args, **kwargs
+
+    ):
+
+        super().__init__(*args, **kwargs)
+
+        self.pre_tokenizer = pre_tokenizer
+
+    def _tokenize(self, text, *arg, **kwargs):
+
+        split_tokens = []
+
+        for text in self.pre_tokenizer(text):
+
+            if text in self.vocab:
+
+                split_tokens.append(text)
+
+            else:
+
+                split_tokens.extend(super()._tokenize(text))
+
+        return split_tokens
+
+model = BigBirdModel.from_pretrained('Lowin/chinese-bigbird-small')
+
+tokenizer = JiebaTokenizer.from_pretrained('Lowin/chinese-bigbird-small')
+
+```
+
+https://github.com/LowinLi/chinese-bigbird

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/home/lilongwei/chinese-bigbird-small/",
+  "architectures": [
+    "BigBirdModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu_fast",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1024,
+  "model_type": "big_bird",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "num_random_blocks": 3,
+  "pad_token_id": 0,
+  "rescale_embeddings": false,
+  "sep_token_id": 66,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.0",
+  "type_vocab_size": 2,
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8478dd9309c3268a0f3f5d1c741aecf10f6068c715f5843659acca6f073b4f78
+size 165491767

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/home/lilongwei/chinese-bigbird-small/", "tokenizer_class": "JiebaTokenizer"}