fix tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +0 -3
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": true,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
@@ -37,7 +35,6 @@
|
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"spaces_between_special_tokens": false,
|
| 39 |
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
-
"tokenizer_file": "/root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/78814a934d8ce59ee93599378f3e929ff137da06/tokenizer.json",
|
| 41 |
"unk_token": "<unk>",
|
| 42 |
"use_default_system_prompt": true
|
| 43 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
|
|
| 35 |
"sp_model_kwargs": {},
|
| 36 |
"spaces_between_special_tokens": false,
|
| 37 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 38 |
"unk_token": "<unk>",
|
| 39 |
"use_default_system_prompt": true
|
| 40 |
}
|