Upload tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +5 -0
- tokenizer_config.json +12 -4
- vocab.json +0 -0
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -1,12 +1,20 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"bos_token": "<|endoftext|>",
|
|
|
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
-
"
|
| 7 |
-
"is_local": false,
|
| 8 |
"model_max_length": 1024,
|
| 9 |
-
"pad_token": null,
|
| 10 |
"tokenizer_class": "GPT2Tokenizer",
|
| 11 |
"unk_token": "<|endoftext|>"
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
|
|
|
| 17 |
"model_max_length": 1024,
|
|
|
|
| 18 |
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
"unk_token": "<|endoftext|>"
|
| 20 |
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|