Upload 4 files
Browse files- tokenizer.json +0 -0
- tokenizer.model +2 -2
- tokenizer_config.json +3 -11
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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:abd5ba2b312cd47f8bcc2b183d792c474210770920f676ca26f121a67a4a25bc
|
| 3 |
+
size 485442
|
tokenizer_config.json
CHANGED
|
@@ -1,17 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
-
"add_eos_token":
|
| 4 |
"add_prefix_space": true,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
-
"content": "<pad>",
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": false,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false,
|
| 12 |
-
"special": true
|
| 13 |
-
},
|
| 14 |
-
"1": {
|
| 15 |
"content": "<unk>",
|
| 16 |
"lstrip": false,
|
| 17 |
"normalized": false,
|
|
@@ -19,7 +11,7 @@
|
|
| 19 |
"single_word": false,
|
| 20 |
"special": true
|
| 21 |
},
|
| 22 |
-
"
|
| 23 |
"content": "<s>",
|
| 24 |
"lstrip": false,
|
| 25 |
"normalized": false,
|
|
@@ -41,7 +33,7 @@
|
|
| 41 |
"eos_token": "</s>",
|
| 42 |
"legacy": true,
|
| 43 |
"model_max_length": 1000000000000000019884624838656,
|
| 44 |
-
"pad_token":
|
| 45 |
"sp_model_kwargs": {},
|
| 46 |
"spaces_between_special_tokens": false,
|
| 47 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"add_prefix_space": true,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"content": "<unk>",
|
| 8 |
"lstrip": false,
|
| 9 |
"normalized": false,
|
|
|
|
| 11 |
"single_word": false,
|
| 12 |
"special": true
|
| 13 |
},
|
| 14 |
+
"1": {
|
| 15 |
"content": "<s>",
|
| 16 |
"lstrip": false,
|
| 17 |
"normalized": false,
|
|
|
|
| 33 |
"eos_token": "</s>",
|
| 34 |
"legacy": true,
|
| 35 |
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": null,
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"spaces_between_special_tokens": false,
|
| 39 |
"tokenizer_class": "LlamaTokenizer",
|