Instructions to use Intel/dynamic-minilmv2-L6-H384-squad1.1-int8-static with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Intel/dynamic-minilmv2-L6-H384-squad1.1-int8-static with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="Intel/dynamic-minilmv2-L6-H384-squad1.1-int8-static")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Intel/dynamic-minilmv2-L6-H384-squad1.1-int8-static") model = AutoModelForQuestionAnswering.from_pretrained("Intel/dynamic-minilmv2-L6-H384-squad1.1-int8-static", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "add_prefix_space": false, | |
| "bos_token": "<s>", | |
| "cls_token": "<s>", | |
| "do_lower_case": true, | |
| "eos_token": "</s>", | |
| "errors": "replace", | |
| "mask_token": "<mask>", | |
| "model_max_length": 512, | |
| "name_or_path": "sguskin/dynamic-minilmv2-L6-H384-squad1.1", | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "special_tokens_map_file": null, | |
| "tokenizer_class": "RobertaTokenizer", | |
| "trim_offsets": true, | |
| "unk_token": "<unk>" | |
| } | |