Delete tokenizer_config.json
Browse files- tokenizer_config.json +0 -30
tokenizer_config.json
DELETED
|
@@ -1,30 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"additional_special_tokens": [
|
| 4 |
-
"<|endoftext|>",
|
| 5 |
-
"<fim_prefix>",
|
| 6 |
-
"<fim_middle>",
|
| 7 |
-
"<fim_suffix>",
|
| 8 |
-
"<fim_pad>",
|
| 9 |
-
"<filename>",
|
| 10 |
-
"<gh_stars>",
|
| 11 |
-
"<issue_start>",
|
| 12 |
-
"<issue_comment>",
|
| 13 |
-
"<issue_closed>",
|
| 14 |
-
"<jupyter_start>",
|
| 15 |
-
"<jupyter_text>",
|
| 16 |
-
"<jupyter_code>",
|
| 17 |
-
"<jupyter_output>",
|
| 18 |
-
"<empty_output>",
|
| 19 |
-
"<commit_before>",
|
| 20 |
-
"<commit_msg>",
|
| 21 |
-
"<commit_after>",
|
| 22 |
-
"<reponame>"
|
| 23 |
-
],
|
| 24 |
-
"bos_token": "<|endoftext|>",
|
| 25 |
-
"eos_token": "<|endoftext|>",
|
| 26 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 27 |
-
"tokenizer_class": "GPT2Tokenizer",
|
| 28 |
-
"unk_token": "<|endoftext|>",
|
| 29 |
-
"vocab_size": 49152
|
| 30 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|