add tokenizer
Browse files- .gitattributes +1 -0
- merges.txt +0 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +33 -0
- vocab.json +3 -0
.gitattributes
CHANGED
|
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 30 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 30 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
vocab.json filter=lfs diff=lfs merge=lfs -text
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"mask_token": "<mask>",
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
+
"unk_token": "<unk>"
|
| 7 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"eos_token": {
|
| 13 |
+
"__type": "AddedToken",
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"errors": "replace",
|
| 21 |
+
"name_or_path": "./gpt2_ur_small/",
|
| 22 |
+
"pad_token": null,
|
| 23 |
+
"special_tokens_map_file": "/root/.cache/huggingface/transformers/fd05696fd7c524ed400d964c4d1fa66c6435bc0d588c55f7ac98c7c850c7cc5a.b7f8742f1d370b815979aeabc401aed45c79760724667d2725ac7503c242b97f",
|
| 24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<|endoftext|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab6656bcf981ae51e1548a3879bf0ddc1167b1605dbaaccb71c7dcb5f8240e31
|
| 3 |
+
size 10897434
|