Upload tokenizer
Browse files- .gitattributes +1 -0
- tokenizer.json +3 -0
- tokenizer_config.json +1 -1
.gitattributes
CHANGED
|
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52b081922226132b1e8408182a64d69779463959ecad8097a0333c3923e7cd74
|
| 3 |
+
size 14500838
|
tokenizer_config.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"bos_token": "<s>",
|
|
|
|
| 4 |
"eos_token": "</s>",
|
| 5 |
"model_max_length": 1024,
|
| 6 |
"pad_token": "<pad>",
|
| 7 |
"padding_side": "right",
|
| 8 |
-
"special_tokens_map_file": null,
|
| 9 |
"tokenizer_class": "BloomTokenizer",
|
| 10 |
"trunction_side": "right",
|
| 11 |
"unk_token": "<unk>"
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"model_max_length": 1024,
|
| 7 |
"pad_token": "<pad>",
|
| 8 |
"padding_side": "right",
|
|
|
|
| 9 |
"tokenizer_class": "BloomTokenizer",
|
| 10 |
"trunction_side": "right",
|
| 11 |
"unk_token": "<unk>"
|