debeberta train withnew spm tokenizer

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "checkpoints/deberta-vie-small_spm-3",
+  "architectures": [
+    "DebertaV2ForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": null,
+  "position_biased_input": true,
+  "relative_attention": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.1",
+  "type_vocab_size": 0,
+  "vocab_size": 45000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37d732e29b13b620fbe04738f3949972681eb7eca7acdd2724e0c365813049fc
+size 312514285

tokenizer_config.json

@@ -4,9 +4,11 @@
   "do_lower_case": false,
   "eos_token": "[EOS]",
   "mask_token": "[MASK]",
+  "name_or_path": "checkpoints/deberta-vie-small_spm-3",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/viet/.cache/huggingface/hub/models--hieule--spm-vie-deberta/snapshots/158afb4892bb8ed8ccdcfe9e60aa9a410d6a5325/special_tokens_map.json",
   "split_by_punct": false,
   "tokenizer_class": "DebertaV2Tokenizer",
   "unk_token": "[UNK]"