Upload tokenizer

README.md

@@ -1,13 +1,13 @@
 ---
-license: apache-2.0
+base_model: Qwen/Qwen2-0.5B-Instruct
+datasets:
+- generator
 library_name: peft
+license: apache-2.0
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: Qwen/Qwen2-0.5B-Instruct
-datasets:
-- generator
 model-index:
 - name: qwen2
  results: []

special_tokens_map.json

@@ -10,5 +10,11 @@
  "rstrip": false,
  "single_word": false
  },
- "pad_token": "<|im_end|>"
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
 }

tokenizer_config.json

@@ -35,8 +35,8 @@
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|im_end|>",
  "errors": "replace",
- "model_max_length": 2048,
- "pad_token": "<|im_end|>",
+ "model_max_length": 32768,
+ "pad_token": "<|endoftext|>",
  "split_special_tokens": false,
  "tokenizer_class": "Qwen2Tokenizer",
  "unk_token": null