Upload 6 files

config.json

@@ -6,16 +6,16 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": null,
+  "bos_token_id": 0,
   "classifier_activation": "gelu",
   "classifier_bias": false,
   "classifier_dropout": 0.0,
   "classifier_pooling": "mean",
-  "cls_token_id": 2,
+  "cls_token_id": 0,
   "decoder_bias": true,
   "deterministic_flash_attn": false,
   "embedding_dropout": 0.0,
-  "eos_token_id": null,
+  "eos_token_id": 2,
   "global_attn_every_n_layers": 3,
   "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,
@@ -36,16 +36,16 @@
   "norm_eps": 1e-05,
   "num_attention_heads": 12,
   "num_hidden_layers": 22,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "reference_compile": false,
   "repad_logits_with_grad": false,
-  "sep_token_id": 3,
+  "sep_token_id": 2,
   "sparse_pred_ignore_index": -100,
   "sparse_prediction": false,
-  "tokenizer_class": "ElectraTokenizerFast",
+  "tokenizer_class": "RobertaTokenizerFast",
   "torch_dtype": "float32",
   "transformers_version": "4.48.1",
-  "unk_token_id": 1,
-  "vocab_size": 96105
+  "unk_token_id": 3,
+  "vocab_size": 50265
 }

special_tokens_map.json

@@ -1,7 +1,51 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,58 +1,59 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "[UNK]",
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "[CLS]",
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "3": {
-      "content": "[SEP]",
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "4": {
-      "content": "[MASK]",
-      "lstrip": false,
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "mask_token": "[MASK]",
-  "model_max_length": 128,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": false,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "ElectraTokenizer",
-  "unk_token": "[UNK]"
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }