full sample tokenizer
Browse files- added_tokens.json +1 -1
- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
added_tokens.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"<UNK>": 50257, "<
|
|
|
1 |
+
{"<UNK>": 50257, "<SEP>": 50258, "<PAD>": 50259}
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token":
|
|
|
1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<UNK>", "sep_token": "<SEP>", "pad_token": "<PAD>"}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"unk_token":
|
|
|
1 |
+
{"unk_token": "<UNK>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "pad_token": "<PAD>", "sep_token": "<SEP>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2-medium", "tokenizer_class": "GPT2Tokenizer"}
|