smangrul commited on
Commit
9c94542
1 Parent(s): bd70319

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +4 -4
  2. tokenizer_config.json +2 -2
special_tokens_map.json CHANGED
@@ -11,12 +11,12 @@
11
  "rstrip": false,
12
  "single_word": false
13
  },
14
- "eos_token": {
15
- "content": "<|end_of_text|>",
 
16
  "lstrip": false,
17
  "normalized": false,
18
  "rstrip": false,
19
  "single_word": false
20
- },
21
- "pad_token": "<pad>"
22
  }
 
11
  "rstrip": false,
12
  "single_word": false
13
  },
14
+ "eos_token": "<|eot_id|>",
15
+ "pad_token": {
16
+ "content": "<pad>",
17
  "lstrip": false,
18
  "normalized": false,
19
  "rstrip": false,
20
  "single_word": false
21
+ }
 
22
  }
tokenizer_config.json CHANGED
@@ -2079,9 +2079,9 @@
2079
  "<pad>"
2080
  ],
2081
  "bos_token": "<|begin_of_text|>",
2082
- "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 }}{% if loop.last and add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}{% endfor %}",
2083
  "clean_up_tokenization_spaces": true,
2084
- "eos_token": "<|end_of_text|>",
2085
  "model_input_names": [
2086
  "input_ids",
2087
  "attention_mask"
 
2079
  "<pad>"
2080
  ],
2081
  "bos_token": "<|begin_of_text|>",
2082
+ "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 }}{% if loop.last and add_generation_prompt %}{{ '<|start_header_id|>' }}{% endif %}{% endfor %}",
2083
  "clean_up_tokenization_spaces": true,
2084
+ "eos_token": "<|eot_id|>",
2085
  "model_input_names": [
2086
  "input_ids",
2087
  "attention_mask"