Commit
•
a249ae9
1
Parent(s):
167c004
add tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- 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 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/content/drive/MyDrive/Colab Notebooks_b/modeliai/wiki_10_validate", "tokenizer_class": "GPT2Tokenizer"}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|