Upload 8 files

BASE tokenizer with good hints

config.json

@@ -39,5 +39,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
   "use_cache": true,
-  "vocab_size": 26684
+  "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f97c14f372cc9d72d45477275c434393a7524198b9399455a256cc7f6363485
-size 425391450
+oid sha256:55890a5427eedfa0b1b155c2d3a783885e2d146ff492badeb1c5422338117055
+size 497805594

special_tokens_map.json

@@ -1,5 +1,30 @@
 {
-  "eos_token": "<|EOS|>",
-  "pad_token": "<|PAD|>",
-  "unk_token": "<|UNK|>"
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,34 +1,22 @@
 {
+  "add_bos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<|EOS|>",
+      "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<|PAD|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "<|UNK|>",
-      "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|EOS|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
   "model_max_length": 1024,
-  "pad_token": "<|PAD|>",
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "<|UNK|>"
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
 }