Commit
•
49bf4a5
1
Parent(s):
00ad931
fixed tokenizer - original Gamma tokenizer
Browse files- special_tokens_map.json +3 -28
- tokenizer.json +0 -0
- tokenizer_config.json +1 -10
special_tokens_map.json
CHANGED
|
@@ -1,30 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "</s>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": {
|
| 17 |
-
"content": "<unk>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
-
"unk_token": {
|
| 24 |
-
"content": "<unk>",
|
| 25 |
-
"lstrip": false,
|
| 26 |
-
"normalized": false,
|
| 27 |
-
"rstrip": false,
|
| 28 |
-
"single_word": false
|
| 29 |
-
}
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -23,14 +23,6 @@
|
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
-
},
|
| 27 |
-
"120073": {
|
| 28 |
-
"content": "<|extra_idx|>",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": false
|
| 34 |
}
|
| 35 |
},
|
| 36 |
"additional_special_tokens": [],
|
|
@@ -39,8 +31,7 @@
|
|
| 39 |
"eos_token": "</s>",
|
| 40 |
"legacy": true,
|
| 41 |
"model_max_length": 1000000000000000019884624838656,
|
| 42 |
-
"pad_token":
|
| 43 |
-
"padding_side": "right",
|
| 44 |
"sp_model_kwargs": {},
|
| 45 |
"spaces_between_special_tokens": false,
|
| 46 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
| 27 |
},
|
| 28 |
"additional_special_tokens": [],
|
|
|
|
| 31 |
"eos_token": "</s>",
|
| 32 |
"legacy": true,
|
| 33 |
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": null,
|
|
|
|
| 35 |
"sp_model_kwargs": {},
|
| 36 |
"spaces_between_special_tokens": false,
|
| 37 |
"tokenizer_class": "LlamaTokenizer",
|