Upload tokenizer
Browse files- tokenizer.json +2 -16
- tokenizer_config.json +0 -7
tokenizer.json
CHANGED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 128,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 128
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 2,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "<|im_end|>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -146,16 +146,9 @@
|
|
| 146 |
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 147 |
"clean_up_tokenization_spaces": false,
|
| 148 |
"eos_token": "<|im_end|>",
|
| 149 |
-
"max_length": 128,
|
| 150 |
"model_max_length": 2048,
|
| 151 |
-
"pad_to_multiple_of": null,
|
| 152 |
"pad_token": "<|im_end|>",
|
| 153 |
-
"pad_token_type_id": 0,
|
| 154 |
-
"padding_side": "right",
|
| 155 |
-
"stride": 0,
|
| 156 |
"tokenizer_class": "GPT2Tokenizer",
|
| 157 |
-
"truncation_side": "right",
|
| 158 |
-
"truncation_strategy": "longest_first",
|
| 159 |
"unk_token": "<|endoftext|>",
|
| 160 |
"vocab_size": 49152
|
| 161 |
}
|
|
|
|
| 146 |
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 147 |
"clean_up_tokenization_spaces": false,
|
| 148 |
"eos_token": "<|im_end|>",
|
|
|
|
| 149 |
"model_max_length": 2048,
|
|
|
|
| 150 |
"pad_token": "<|im_end|>",
|
|
|
|
|
|
|
|
|
|
| 151 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
|
|
| 152 |
"unk_token": "<|endoftext|>",
|
| 153 |
"vocab_size": 49152
|
| 154 |
}
|