Upload tokenizer

special_tokens_map.json

@@ -13,6 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -34,10 +34,6 @@
   "normalizer": {
     "type": "Sequence",
     "normalizers": [
-      {
-        "type": "Prepend",
-        "prepend": "▁"
-      },
       {
         "type": "Replace",
         "pattern": {

tokenizer_config.json

@@ -1,35 +1,50 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": null,
   "clean_up_tokenization_spaces": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
-  "padding_side": "right",
-  "sp_model_kwargs": {},
+  "cls_token": null,
+  "eos_token": "</s>",
+  "mask_token": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 4096,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sep_token": null,
+  "split_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "truncation_side": "right",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }