Upload 3 files
Browse files- added_tokens.json +13 -0
- tokenizer_config.json +6 -3
added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token":
|
| 3 |
"add_eos_token": true,
|
| 4 |
-
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
"content": "<unk>",
|
|
@@ -117,15 +116,19 @@
|
|
| 117 |
}
|
| 118 |
},
|
| 119 |
"bos_token": "<s>",
|
| 120 |
-
"chat_template": "{% for message in messages %}{% if message['role'] == '
|
| 121 |
"clean_up_tokenization_spaces": false,
|
| 122 |
"eos_token": "<|endoftext|>",
|
| 123 |
"legacy": false,
|
|
|
|
| 124 |
"model_max_length": 4096,
|
| 125 |
"pad_token": "<unk>",
|
| 126 |
"padding_side": "left",
|
| 127 |
"sp_model_kwargs": {},
|
|
|
|
| 128 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 129 |
"unk_token": "<unk>",
|
| 130 |
"use_default_system_prompt": false
|
| 131 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
"add_eos_token": true,
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 116 |
}
|
| 117 |
},
|
| 118 |
"bos_token": "<s>",
|
| 119 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
| 120 |
"clean_up_tokenization_spaces": false,
|
| 121 |
"eos_token": "<|endoftext|>",
|
| 122 |
"legacy": false,
|
| 123 |
+
"max_length": 512,
|
| 124 |
"model_max_length": 4096,
|
| 125 |
"pad_token": "<unk>",
|
| 126 |
"padding_side": "left",
|
| 127 |
"sp_model_kwargs": {},
|
| 128 |
+
"stride": 0,
|
| 129 |
"tokenizer_class": "LlamaTokenizer",
|
| 130 |
+
"truncation_side": "right",
|
| 131 |
+
"truncation_strategy": "longest_first",
|
| 132 |
"unk_token": "<unk>",
|
| 133 |
"use_default_system_prompt": false
|
| 134 |
}
|