Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +1 -2
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
"content": "<unk>",
|
|
@@ -117,9 +116,9 @@
|
|
| 117 |
}
|
| 118 |
},
|
| 119 |
"bos_token": "<s>",
|
|
|
|
| 120 |
"clean_up_tokenization_spaces": false,
|
| 121 |
"eos_token": "<|endoftext|>",
|
| 122 |
-
"extra_special_tokens": {},
|
| 123 |
"legacy": false,
|
| 124 |
"model_max_length": 4096,
|
| 125 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": false,
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 116 |
}
|
| 117 |
},
|
| 118 |
"bos_token": "<s>",
|
| 119 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
| 120 |
"clean_up_tokenization_spaces": false,
|
| 121 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 122 |
"legacy": false,
|
| 123 |
"model_max_length": 4096,
|
| 124 |
"pad_token": "<|endoftext|>",
|