V2 embedding model (federal + foundation) - tokenizer_config.json
Browse files- tokenizer_config.json +15 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": false,
|
| 9 |
+
"model_max_length": 131072,
|
| 10 |
+
"pad_token": "<|endoftext|>",
|
| 11 |
+
"padding_side": "left",
|
| 12 |
+
"split_special_tokens": false,
|
| 13 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 14 |
+
"unk_token": null
|
| 15 |
+
}
|