Added processor with 128 tokens
Browse files- tokenizer.json +8 -1
- tokenizer_config.json +2 -1
- vocab.json +0 -0
tokenizer.json
CHANGED
|
@@ -1,7 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
-
"padding":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 49406,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
+
"padding": {
|
| 5 |
+
"strategy": "BatchLongest",
|
| 6 |
+
"direction": "Right",
|
| 7 |
+
"pad_to_multiple_of": null,
|
| 8 |
+
"pad_id": 49407,
|
| 9 |
+
"pad_type_id": 0,
|
| 10 |
+
"pad_token": "<|endoftext|>"
|
| 11 |
+
},
|
| 12 |
"added_tokens": [
|
| 13 |
{
|
| 14 |
"id": 49406,
|
tokenizer_config.json
CHANGED
|
@@ -24,8 +24,9 @@
|
|
| 24 |
"eos_token": "<|endoftext|>",
|
| 25 |
"errors": "replace",
|
| 26 |
"extra_special_tokens": {},
|
| 27 |
-
"model_max_length":
|
| 28 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 29 |
"tokenizer_class": "CLIPTokenizer",
|
| 30 |
"unk_token": "<|endoftext|>"
|
| 31 |
}
|
|
|
|
| 24 |
"eos_token": "<|endoftext|>",
|
| 25 |
"errors": "replace",
|
| 26 |
"extra_special_tokens": {},
|
| 27 |
+
"model_max_length": 128,
|
| 28 |
"pad_token": "<|endoftext|>",
|
| 29 |
+
"processor_class": "CLIPProcessor",
|
| 30 |
"tokenizer_class": "CLIPTokenizer",
|
| 31 |
"unk_token": "<|endoftext|>"
|
| 32 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|