Upload tokenizer
Browse files- .gitattributes +1 -0
- tokenizer.json +3 -0
- tokenizer_config.json +23 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
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:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497
|
| 3 |
+
size 33384443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"boi_token": "<start_of_image>",
|
| 4 |
+
"bos_token": "<bos>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eoi_token": "<end_of_image>",
|
| 7 |
+
"eos_token": "<eos>",
|
| 8 |
+
"image_token": "<image_soft_token>",
|
| 9 |
+
"is_local": true,
|
| 10 |
+
"mask_token": "<mask>",
|
| 11 |
+
"model_max_length": 2048,
|
| 12 |
+
"model_specific_special_tokens": {
|
| 13 |
+
"boi_token": "<start_of_image>",
|
| 14 |
+
"eoi_token": "<end_of_image>",
|
| 15 |
+
"image_token": "<image_soft_token>"
|
| 16 |
+
},
|
| 17 |
+
"pad_token": "<pad>",
|
| 18 |
+
"sp_model_kwargs": null,
|
| 19 |
+
"spaces_between_special_tokens": false,
|
| 20 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 21 |
+
"unk_token": "<unk>",
|
| 22 |
+
"use_default_system_prompt": false
|
| 23 |
+
}
|