FEAT: first commit

.gitattributes

@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,21 @@
+{
+    "architectures": [
+        "MegatronBertForMaskedLM"
+    ],
+    "vocab_size": 21248,
+    "hidden_size": 2560,
+    "num_hidden_layers": 48,
+    "num_attention_heads": 40,
+    "hidden_act": "gelu",
+    "intermediate_size": 10240,
+    "hidden_dropout_prob": 0.1,
+    "attention_probs_dropout_prob": 0.1,
+    "max_position_embeddings": 512,
+    "type_vocab_size": 2,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-12,
+    "gradient_checkpointing": false,
+    "position_embedding_type": "absolute",
+    "use_cache": false,
+    "model_type": "megatron-bert"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a7bbc7c726ebbe1f7a260171f1190f16ba1fff40610b059ddc8b1c9e1244b45
+size 7690876653

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+    
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "name_or_path": "/cognitive_comp/gaoxinyu/hf_hub/Erlangshen-MegatronBert-3.9B",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}