update pad token & eos token

#5
Files changed (2) hide show
  1. config.json +2 -1
  2. tokenizer_config.json +2 -1
config.json CHANGED
@@ -6,7 +6,8 @@
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
- "eos_token_id": 128001,
 
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
 
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "pad_token_id": 128001,
11
  "hidden_act": "silu",
12
  "hidden_size": 4096,
13
  "initializer_range": 0.02,
tokenizer_config.json CHANGED
@@ -2049,10 +2049,11 @@
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 %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2054
  "clean_up_tokenization_spaces": true,
2055
- "eos_token": "<|end_of_text|>",
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"
 
2049
  "special": true
2050
  }
2051
  },
2052
+ "pad_token" : "<|end_of_text|>",
2053
  "bos_token": "<|begin_of_text|>",
2054
  "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 %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2055
  "clean_up_tokenization_spaces": true,
2056
+ "eos_token": "<|eot_id|>",
2057
  "model_input_names": [
2058
  "input_ids",
2059
  "attention_mask"