danielhanchen commited on
Commit
aa94a9c
1 Parent(s): e9af1ab

Upload tokenizer

Browse files
Files changed (3) hide show
  1. README.md +0 -1
  2. special_tokens_map.json +2 -1
  3. tokenizer_config.json +3 -2
README.md CHANGED
@@ -8,7 +8,6 @@ tags:
8
  - transformers
9
  - llama
10
  - llama-3
11
-
12
  ---
13
 
14
  # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
 
8
  - transformers
9
  - llama
10
  - llama-3
 
11
  ---
12
 
13
  # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
special_tokens_map.json CHANGED
@@ -12,5 +12,6 @@
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
- }
 
16
  }
 
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
  }
tokenizer_config.json CHANGED
@@ -2050,7 +2050,7 @@
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": [
@@ -2058,6 +2058,7 @@
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 8192,
2061
- "padding_side": "right",
 
2062
  "tokenizer_class": "PreTrainedTokenizerFast"
2063
  }
 
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
  "model_input_names": [
 
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 8192,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "padding_side": "left",
2063
  "tokenizer_class": "PreTrainedTokenizerFast"
2064
  }