Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +8 -0
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"content": "<|endoftext|>",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
+
"content": "<|unk|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
"content": "<|endoftext|>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|