Instructions to use BAAI/bge-base-zh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BAAI/bge-base-zh with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="BAAI/bge-base-zh")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("BAAI/bge-base-zh") model = AutoModel.from_pretrained("BAAI/bge-base-zh") - Inference
- Notebooks
- Google Colab
- Kaggle
Commit ·
faefe59
1
Parent(s): 3f9190f
Fix `model_max_length` in `tokenizer_config.json` (#1)
Browse files- Fix `model_max_length` in `tokenizer_config.json` (10fe8e24d5e0bbdfdcbadfb6760e2df1adb00590)
Co-authored-by: Santiago Castro <bryant1410@users.noreply.huggingface.co>
- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"do_basic_tokenize": true,
|
| 5 |
"do_lower_case": true,
|
| 6 |
"mask_token": "[MASK]",
|
| 7 |
-
"model_max_length":
|
| 8 |
"never_split": null,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
|
|
|
| 4 |
"do_basic_tokenize": true,
|
| 5 |
"do_lower_case": true,
|
| 6 |
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 512,
|
| 8 |
"never_split": null,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|