MagiBoss commited on
Commit
5db0fb4
·
1 Parent(s): 67c8398

Upload processor

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +7 -1
  2. tokenizer_config.json +9 -0
special_tokens_map.json CHANGED
@@ -13,5 +13,11 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|end_of_text|>"
 
 
 
 
 
 
17
  }
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
tokenizer_config.json CHANGED
@@ -2047,12 +2047,21 @@
2047
  "rstrip": false,
2048
  "single_word": false,
2049
  "special": true
 
 
 
 
 
 
 
 
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
  "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 %}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|end_of_text|>",
 
2056
  "max_seq_length": 4096,
2057
  "model_input_names": [
2058
  "input_ids",
 
2047
  "rstrip": false,
2048
  "single_word": false,
2049
  "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<image>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
  }
2059
  },
2060
  "bos_token": "<|begin_of_text|>",
2061
  "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 %}",
2062
  "clean_up_tokenization_spaces": true,
2063
  "eos_token": "<|end_of_text|>",
2064
+ "extra_special_tokens": {},
2065
  "max_seq_length": 4096,
2066
  "model_input_names": [
2067
  "input_ids",