Instructions to use naot97/my-tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use naot97/my-tokenizer with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("naot97/my-tokenizer", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload tokenizer
Browse files- added_tokens.json +0 -0
- special_tokens_map.json +2 -12
- tokenizer.json +2 -2
- tokenizer.model +2 -2
- tokenizer_config.json +0 -0
added_tokens.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,23 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"boi_token": "<start_of_image>",
|
| 3 |
"bos_token": {
|
| 4 |
-
"content": "<
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false
|
| 9 |
},
|
| 10 |
-
"eoi_token": "<end_of_image>",
|
| 11 |
"eos_token": {
|
| 12 |
-
"content": "<
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false
|
| 17 |
-
},
|
| 18 |
-
"image_token": "<image_soft_token>",
|
| 19 |
-
"pad_token": {
|
| 20 |
-
"content": "<pad>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
"normalized": false,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
|
|
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96ba17c45c5c207506efe2a3e5267fd4d590094a50c42b43f60be25092ab466e
|
| 3 |
+
size 5248888
|
tokenizer.model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|