Upload tokenizer
Browse files- tokenizer_config.json +2 -2
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
@@ -33,7 +34,7 @@
|
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
"eos_token": "</s>",
|
| 35 |
"legacy": true,
|
| 36 |
-
"max_length":
|
| 37 |
"model_max_length": 2048,
|
| 38 |
"pad_token": "<unk>",
|
| 39 |
"sp_model_kwargs": {},
|
|
@@ -42,7 +43,6 @@
|
|
| 42 |
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
"truncation_side": "right",
|
| 44 |
"truncation_strategy": "longest_first",
|
| 45 |
-
"trust_remote_code": false,
|
| 46 |
"unk_token": "<unk>",
|
| 47 |
"use_default_system_prompt": false,
|
| 48 |
"use_fast": true
|
|
|
|
| 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>",
|
|
|
|
| 34 |
"clean_up_tokenization_spaces": false,
|
| 35 |
"eos_token": "</s>",
|
| 36 |
"legacy": true,
|
| 37 |
+
"max_length": 1536,
|
| 38 |
"model_max_length": 2048,
|
| 39 |
"pad_token": "<unk>",
|
| 40 |
"sp_model_kwargs": {},
|
|
|
|
| 43 |
"tokenizer_class": "LlamaTokenizer",
|
| 44 |
"truncation_side": "right",
|
| 45 |
"truncation_strategy": "longest_first",
|
|
|
|
| 46 |
"unk_token": "<unk>",
|
| 47 |
"use_default_system_prompt": false,
|
| 48 |
"use_fast": true
|