Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +5 -1
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:476b711d0ef387ddcdaae99abb9686498fdff008d33308d865970b0815c6c4d0
|
| 3 |
+
size 17210394
|
tokenizer_config.json
CHANGED
|
@@ -2073,11 +2073,15 @@
|
|
| 2073 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 2074 |
"clean_up_tokenization_spaces": true,
|
| 2075 |
"eos_token": "<|im_end|>",
|
|
|
|
| 2076 |
"model_input_names": [
|
| 2077 |
"input_ids",
|
| 2078 |
"attention_mask"
|
| 2079 |
],
|
| 2080 |
"model_max_length": 131072,
|
| 2081 |
"pad_token": "<|im_end|>",
|
| 2082 |
-
"
|
|
|
|
|
|
|
|
|
|
| 2083 |
}
|
|
|
|
| 2073 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 2074 |
"clean_up_tokenization_spaces": true,
|
| 2075 |
"eos_token": "<|im_end|>",
|
| 2076 |
+
"max_length": 512,
|
| 2077 |
"model_input_names": [
|
| 2078 |
"input_ids",
|
| 2079 |
"attention_mask"
|
| 2080 |
],
|
| 2081 |
"model_max_length": 131072,
|
| 2082 |
"pad_token": "<|im_end|>",
|
| 2083 |
+
"stride": 0,
|
| 2084 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2085 |
+
"truncation_side": "right",
|
| 2086 |
+
"truncation_strategy": "longest_first"
|
| 2087 |
}
|