add tokenizer
Browse files- added_tokens.json +1 -0
- merges.txt +0 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<|Step 1|>": 50258, "<|Step 4|>": 50261, "<|Title|>": 50257, "<|Step 2|>": 50259, "<|Step 5|>": 50262, "<|Step 3|>": 50260}
|
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": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "additional_special_tokens": ["<|Title|>", "<|Step 1|>", "<|Step 2|>", "<|Step 3|>", "<|Step 4|>", "<|Step 5|>"]}
|
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": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "./Model_Base/gpt2-large/ResizedAvg/", "tokenizer_class": "GPT2Tokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|