add tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": "/opt/ml/.cache/huggingface/transformers/c2ab65b9d700d0871fd407d489869d7b93f69fb5f1a58fb1fac796fd43b9ea27.1f5b09bb43973b9fbd2ba75c9fe44ffab036b980c4e6a9d779aa7707913416fe", "name_or_path": "/opt/ml/final-project-level3-nlp-08/outputs/checkpoint-110", "tokenizer_class": "GPT2Tokenizer"}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|