fix: tokenizer (#1)

- fix: tokenizer (4f6dc645d331b05dbf5a77abc4fdedb43f7d35e0)

special_tokens_map.json

@@ -1,16 +1,4 @@
 {
-  "bos_token": {
-    "content": "<|begin_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|eot_id|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|end_of_text|>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
-size 17209961
+oid sha256:e134af98b985517b4f068e3755ae90d4e9cd2d45d328325dc503f1c6b2d06cc7
+size 9085698

tokenizer_config.json

@@ -2053,7 +2053,6 @@
   "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
-  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"