Upload tokenizer

special_tokens_map.json

@@ -4,7 +4,7 @@
     "<|im_end|>"
   ],
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab5732ed79313d0aea2e3f4b59b86e16d101b99533e3998ab2ea0f94d6ddf564
-size 11418364
+oid sha256:0e46299e92a327fd4b3b6563245a4546e461f1869a12dc6b7827cfc7e39cd4bf
+size 11418532

tokenizer_config.json

@@ -33,11 +33,18 @@
   "bos_token": null,
   "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "errors": "replace",
+  "max_length": 512,
   "model_max_length": 32768,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "split_special_tokens": false,
+  "stride": 0,
   "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": null
 }