138 lines
4.3 KiB
JSON
138 lines
4.3 KiB
JSON
{
|
|
"add_bos_token": false,
|
|
"add_eos_token": false,
|
|
"add_prefix_space": null,
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "<unk>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"1": {
|
|
"content": "<|startoftext|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"2": {
|
|
"content": "<|endoftext|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"6": {
|
|
"content": "<|im_start|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"7": {
|
|
"content": "<|im_end|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"64000": {
|
|
"content": "<|next_start|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"64001": {
|
|
"content": "<|next_end|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"64002": {
|
|
"content": "<|target_start|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"64003": {
|
|
"content": "<|target_end|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"64004": {
|
|
"content": "<|target|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"64005": {
|
|
"content": "<|search_and_replace|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"additional_special_tokens": [
|
|
"<|im_start|>",
|
|
"<|im_end|>",
|
|
"<|next_start|>",
|
|
"<|next_end|>",
|
|
"<|target_start|>",
|
|
"<|target_end|>",
|
|
"<|target|>",
|
|
"<|search_and_replace|>"
|
|
],
|
|
"bos_token": "<|startoftext|>",
|
|
"chat_template": [
|
|
{
|
|
"name": "default",
|
|
"template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] + '<|im_end|>' }}{% if loop.last and add_generation_prompt %}{{ '\n<|im_start|>assistant\n<|next_start|>' }}{% endif %}{% endfor %}"
|
|
},
|
|
{
|
|
"name": "assistant-conversation",
|
|
"template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] + '<|im_end|>' }}{% if loop.last and add_generation_prompt %}{{ '\n<|im_start|>assistant\n<|next_start|>' }}{% endif %}{% endfor %}"
|
|
},
|
|
{
|
|
"name": "prefix_response",
|
|
"template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] }}{% if not loop.last %}{{ '<|im_end|>' }}{% endif %}{% endfor %}"
|
|
}
|
|
],
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|im_end|>",
|
|
"legacy": true,
|
|
"max_length": 16384,
|
|
"model_max_length": 16384,
|
|
"pad_to_multiple_of": null,
|
|
"pad_token": "<|endoftext|>",
|
|
"pad_token_type_id": 0,
|
|
"padding_side": "left",
|
|
"sp_model_kwargs": {},
|
|
"spaces_between_special_tokens": false,
|
|
"stride": 0,
|
|
"tokenizer_class": "LlamaTokenizer",
|
|
"truncation_side": "right",
|
|
"truncation_strategy": "longest_first",
|
|
"unk_token": "<unk>",
|
|
"use_default_system_prompt": false
|
|
}
|