Update tokenizer_config.json
Browse files- tokenizer_config.json +36 -5
tokenizer_config.json
CHANGED
|
@@ -1,13 +1,44 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
"
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"bos_token": "<|startoftext|>",
|
|
|
|
| 7 |
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
| 8 |
"pad_token": "<unk>",
|
|
|
|
| 9 |
"sp_model_kwargs": {},
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
|
|
|
|
|
|
| 13 |
}
|
|
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<|startoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
"bos_token": "<|startoftext|>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
"eos_token": "<|endoftext|>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 200000,
|
| 35 |
"pad_token": "<unk>",
|
| 36 |
+
"padding_side": "right",
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"truncation_side": "right",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
}
|
| 44 |
+
|