Instructions to use mosaicml/mosaic-bert-base-seqlen-2048 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mosaicml/mosaic-bert-base-seqlen-2048 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="mosaicml/mosaic-bert-base-seqlen-2048", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("mosaicml/mosaic-bert-base-seqlen-2048", trust_remote_code=True) model = AutoModelForMaskedLM.from_pretrained("mosaicml/mosaic-bert-base-seqlen-2048", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Create LICENSE (#4)
Verified signature- Create LICENSE (9f28d436ee44f3ecf229f166226ff5209734552b) Co-authored-by: Kobie Crawford <kobindra@users.noreply.huggingface.co>f136a72
-
Update citation in README
d257607 -
Update Readme to clarify how to load model
f5a307f -
Change attention_probs_dropout_prob to 0.1 so that triton FlashAttention dependencies are avoided
See [github issue](https://github.com/mosaicml/examples/issues/441#issuecomment-1874817465) for more detail2e90941
-
Update config so that alibi_starting_size is explicitly set to 2048
97f26fe
-
Update README.md
99fe917 -
Update README.md
c3d9ccf
-
Update README.md
3a454d2 -
Create README.md
d9748e0 -
Upload BertForMaskedLM
b7a0389 -
initial commit
2e2799a