Upload ModernBERT model

added_tokens.json

@@ -1,7 +1,4 @@
 {
-  "</s>": 30001,
-  "<mask>": 30004,
-  "<pad>": 30003,
-  "<s>": 30000,
-  "<unk>": 30002
+  "</s>": 50001,
+  "<s>": 50000
 }

config.json

@@ -5,7 +5,7 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 30000,
+  "bos_token_id": 50000,
   "classifier_activation": "gelu",
   "classifier_bias": false,
   "classifier_dropout": 0.0,
@@ -14,15 +14,15 @@
   "decoder_bias": true,
   "deterministic_flash_attn": false,
   "embedding_dropout": 0.0,
-  "eos_token_id": 30001,
+  "eos_token_id": 50001,
   "global_attn_every_n_layers": 3,
   "global_rope_theta": 160000.0,
   "hidden_activation": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
+  "hidden_size": 768,
   "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
+  "intermediate_size": 3072,
   "local_attention": 128,
   "local_attention_rope_theta": 10000,
   "local_attention_window": 128,
@@ -33,8 +33,8 @@
   "model_type": "modernbert",
   "norm_bias": false,
   "norm_eps": 1e-05,
-  "num_attention_heads": 8,
-  "num_hidden_layers": 6,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "repad_logits_with_grad": false,
   "rope_theta": 160000,
@@ -44,5 +44,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.53.1",
   "type_vocab_size": 2,
-  "vocab_size": 30005
+  "vocab_size": 50005
 }

special_tokens_map.json

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "cls_token": {
-    "content": "<s>",
+    "content": "[CLS]",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
@@ -21,28 +21,28 @@
     "single_word": false
   },
   "mask_token": {
-    "content": "<mask>",
+    "content": "[MASK]",
     "lstrip": true,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
+    "content": "[PAD]",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "</s>",
+    "content": "[SEP]",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,

tokenizer_config.json

@@ -1,62 +1,78 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "30000": {
-      "content": "<s>",
+    "0": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "30001": {
-      "content": "</s>",
+    "1": {
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "30002": {
-      "content": "<unk>",
+    "2": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "30003": {
-      "content": "<pad>",
+    "3": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "30004": {
-      "content": "<mask>",
+    "4": {
+      "content": "[MASK]",
       "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "50000": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50001": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "<s>",
+  "cls_token": "[CLS]",
   "eos_token": "</s>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "mask_token": "<mask>",
+  "mask_token": "[MASK]",
   "max_length": 256,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "stride": 0,
   "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
-  "unk_token": "<unk>"
+  "unk_token": "[UNK]"
 }