File size: 1,634 Bytes
40276ca | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 | {
"added_tokens_decoder": {
"128000": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128001": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128006": {
"content": "<|start_header_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128007": {
"content": "<|end_header_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128008": {
"content": "<|eom_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128009": {
"content": "<|eot_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|begin_of_text|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|eot_id|>",
"pad_token": "<|end_of_text|>",
"model_max_length": 131072,
"tokenizer_class": "PreTrainedTokenizerFast",
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' + message['content'] | trim + '<|eot_id|>'}}{% endfor %}{% if add_generation_prompt %}{{'<|start_header_id|>assistant<|end_header_id|>\\n\\n'}}{% endif %}"
}
|