test: gpt2 tokenizer conversion
Browse files- merges.txt +0 -0
- special_tokens_map.json +39 -0
- tokenizer.json +0 -0
- tokenizer_config.json +42 -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 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<|fim_prefix|>",
|
| 5 |
+
"<|fim_middle|>",
|
| 6 |
+
"<|fim_suffix|>",
|
| 7 |
+
"<|fim_pad|>",
|
| 8 |
+
"<gh_stars>",
|
| 9 |
+
"<filename>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<empty_output>",
|
| 18 |
+
"<commit_before>",
|
| 19 |
+
"<commit_msg>",
|
| 20 |
+
"<commit_after>",
|
| 21 |
+
"<reponame>",
|
| 22 |
+
"<|endofprompt|>",
|
| 23 |
+
"<|im_start|>",
|
| 24 |
+
"<|im_end|>",
|
| 25 |
+
"<|pause|>",
|
| 26 |
+
"<|reg0|>",
|
| 27 |
+
"<|reg1|>",
|
| 28 |
+
"<|reg2|>",
|
| 29 |
+
"<|reg3|>",
|
| 30 |
+
"<|reg4|>",
|
| 31 |
+
"<|reg5|>",
|
| 32 |
+
"<|reg6|>",
|
| 33 |
+
"<|reg7|>",
|
| 34 |
+
"<|extra0|>"
|
| 35 |
+
],
|
| 36 |
+
"bos_token": "<|endoftext|>",
|
| 37 |
+
"eos_token": "<|endoftext|>",
|
| 38 |
+
"unk_token": "<|endoftext|>"
|
| 39 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<gh_stars>",
|
| 10 |
+
"<filename>",
|
| 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 |
+
"<|endofprompt|>",
|
| 24 |
+
"<|im_start|>",
|
| 25 |
+
"<|im_end|>",
|
| 26 |
+
"<|pause|>",
|
| 27 |
+
"<|reg0|>",
|
| 28 |
+
"<|reg1|>",
|
| 29 |
+
"<|reg2|>",
|
| 30 |
+
"<|reg3|>",
|
| 31 |
+
"<|reg4|>",
|
| 32 |
+
"<|reg5|>",
|
| 33 |
+
"<|reg6|>",
|
| 34 |
+
"<|reg7|>",
|
| 35 |
+
"<|extra0|>"
|
| 36 |
+
],
|
| 37 |
+
"bos_token": "<|endoftext|>",
|
| 38 |
+
"clean_up_tokenization_spaces": true,
|
| 39 |
+
"eos_token": "<|endoftext|>",
|
| 40 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 41 |
+
"unk_token": "<|endoftext|>"
|
| 42 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|