Initial version of rembert

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "artefacts/pt_model",
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 312,
+  "embedding_dropout_prob": 0,
+  "embedding_size": 256,
+  "eos_token_id": 313,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "input_embedding_size": 256,
+  "intermediate_size": 4608,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "rembert",
+  "num_attention_heads": 18,
+  "num_hidden_layers": 32,
+  "output_embedding_size": 1664,
+  "pad_token_id": 0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.4.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250300
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d06ccca502501049b074a324ea1645b8b683ebf5feb0ff47045567ed5e07e06
+size 2303882157

sentencepiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ce12ea4550e57af39217a75686a61695e34edbb1c9892f82f0b861d73a4482
+size 4697711

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1eec3888d83176ea2abf1676afb103b8da383ed9a3d506d97fd1c7c21cc3365
+size 2304351976

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "special_tokens_map_file": null, "name_or_path": "artefacts/", "tokenizer_file": null}