Instructions to use nreimers/MiniLM-L6-H384-uncased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nreimers/MiniLM-L6-H384-uncased with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nreimers/MiniLM-L6-H384-uncased")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("nreimers/MiniLM-L6-H384-uncased") model = AutoModel.from_pretrained("nreimers/MiniLM-L6-H384-uncased", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
up
Browse files- README.md +6 -6
- tokenizer_config.json +1 -1
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
| 4 |
-
|
| 5 |
-
## MiniLM: 6 Layer Version
|
| 6 |
-
|
| 7 |
This is a 6 layer version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased/) by keeping only every second layer.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
## MiniLM: 6 Layer Version
|
| 6 |
+
|
| 7 |
This is a 6 layer version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased/) by keeping only every second layer.
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "name_or_path": "microsoft/MiniLM-L12-H384-uncased", "do_basic_tokenize": true, "never_split": null, "model_max_length": 512}
|