simpler tokenizer

config.json

@@ -26,5 +26,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.1",
   "use_cache": true,
-  "vocab_size": 25
+  "vocab_size": 6
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b43fba3a61c14ef075dbe086c7b9239b13b0d843d936e8b3bba923824ad4433
-size 142920
+oid sha256:56b706c1b3d4fff35a09250fce0a43595ec3fe4829184f029f39881699899daf
+size 138048

special_tokens_map.json

@@ -1,51 +1,9 @@
 {
-  "bos_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -1,16 +1,7 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": {
-    "strategy": {
-      "Fixed": 10
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 3,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,
@@ -168,26 +159,7 @@
       "[SEP]": 2,
       "[PAD]": 3,
       "[MASK]": 4,
-      ".": 5,
-      "this": 6,
-      "sentence": 7,
-      "is": 8,
-      "one": 9,
-      "the": 10,
-      "2": 11,
-      "#)": 12,
-      "3": 13,
-      "numbers": 14,
-      "symbols": 15,
-      "first": 16,
-      "contains": 17,
-      "1": 18,
-      "not": 19,
-      "but": 20,
-      "second": 21,
-      "(": 22,
-      "and": 23,
-      "over": 24
+      "token": 5
     },
     "unk_token": "[UNK]"
   }

tokenizer_config.json

@@ -47,11 +47,9 @@
   "cls_token": "[CLS]",
   "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "max_length": 1048576,
+  "max_new_tokens": 1048576,
   "model_max_length": 1048576,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
   "padding_side": "right",
   "sep_token": "[SEP]",
   "tokenizer_class": "PreTrainedTokenizerFast",