Upload tokenizer
#9
by
ArthurZ
HF staff
- opened
- tokenizer_config.json +7 -0
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
|
|
|
| 4 |
"bos_token": {
|
| 5 |
"__type": "AddedToken",
|
| 6 |
"content": "<s>",
|
|
@@ -18,10 +19,16 @@
|
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
|
|
|
|
|
|
| 21 |
"legacy": null,
|
|
|
|
| 22 |
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
"pad_token": null,
|
|
|
|
| 24 |
"sp_model_kwargs": {},
|
|
|
|
|
|
|
| 25 |
"tokenizer_class": "CodeLlamaTokenizer",
|
| 26 |
"unk_token": {
|
| 27 |
"__type": "AddedToken",
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
| 4 |
+
"additional_special_tokens": [],
|
| 5 |
"bos_token": {
|
| 6 |
"__type": "AddedToken",
|
| 7 |
"content": "<s>",
|
|
|
|
| 19 |
"rstrip": false,
|
| 20 |
"single_word": false
|
| 21 |
},
|
| 22 |
+
"eot_token": null,
|
| 23 |
+
"fill_token": "<FILL_ME>",
|
| 24 |
"legacy": null,
|
| 25 |
+
"middle_token": null,
|
| 26 |
"model_max_length": 1000000000000000019884624838656,
|
| 27 |
"pad_token": null,
|
| 28 |
+
"prefix_token": null,
|
| 29 |
"sp_model_kwargs": {},
|
| 30 |
+
"suffix_first": false,
|
| 31 |
+
"suffix_token": null,
|
| 32 |
"tokenizer_class": "CodeLlamaTokenizer",
|
| 33 |
"unk_token": {
|
| 34 |
"__type": "AddedToken",
|