Create tokenizer_config.json
Browse files- tokenizer_config.json +52 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<|user|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<|assistant|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<|system|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"bos_token": "<|endoftext|>",
|
| 40 |
+
"chat_template": "{%- set ns = namespace(messages=[], system_prompt='') -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{%- set ns.system_prompt = message['content'] -%}{%- else -%}{%- set ns.messages = ns.messages + [message] -%}{%- endif -%}{%- endfor -%}{%- if ns.system_prompt != '' -%}{%- set system_message = '<|system|>\\n' + ns.system_prompt + '\\n' -%}{%- else -%}{%- set system_message = '' -%}{%- endif -%}{%- for message in ns.messages -%}{%- if message['role'] == 'user' -%}{{ '<|user|>\\n' + message['content'] + '\\n' }}{%- elif message['role'] == 'assistant' -%}{{ '<|assistant|>\\n' + message['content'] + '\\n' }}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{ '<|assistant|>\\n' }}{%- endif -%}",
|
| 41 |
+
"clean_up_tokenization_spaces": false,
|
| 42 |
+
"eos_token": "<|endoftext|>",
|
| 43 |
+
"legacy": false,
|
| 44 |
+
"model_max_length": 8192,
|
| 45 |
+
"pad_token": "<|endoftext|>",
|
| 46 |
+
"padding_side": "right",
|
| 47 |
+
"sp_model_kwargs": {},
|
| 48 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 49 |
+
"trust_remote_code": true,
|
| 50 |
+
"unk_token": null,
|
| 51 |
+
"use_fast": true
|
| 52 |
+
}
|