Upload tokenizer
Browse files- tokenizer_config.json +6 -0
tokenizer_config.json
CHANGED
@@ -34,11 +34,17 @@
|
|
34 |
"eos_token": "</s>",
|
35 |
"extra_special_tokens": {},
|
36 |
"legacy": false,
|
|
|
37 |
"model_max_length": 2048,
|
|
|
38 |
"pad_token": "</s>",
|
|
|
39 |
"padding_side": "right",
|
40 |
"sp_model_kwargs": {},
|
|
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
42 |
"unk_token": "<unk>",
|
43 |
"use_default_system_prompt": false
|
44 |
}
|
|
|
34 |
"eos_token": "</s>",
|
35 |
"extra_special_tokens": {},
|
36 |
"legacy": false,
|
37 |
+
"max_length": 2048,
|
38 |
"model_max_length": 2048,
|
39 |
+
"pad_to_multiple_of": null,
|
40 |
"pad_token": "</s>",
|
41 |
+
"pad_token_type_id": 0,
|
42 |
"padding_side": "right",
|
43 |
"sp_model_kwargs": {},
|
44 |
+
"stride": 0,
|
45 |
"tokenizer_class": "LlamaTokenizer",
|
46 |
+
"truncation_side": "right",
|
47 |
+
"truncation_strategy": "longest_first",
|
48 |
"unk_token": "<unk>",
|
49 |
"use_default_system_prompt": false
|
50 |
}
|