Fill-Mask
Transformers
Safetensors
English
lr_attnres_bert
custom_code
bert
masked-lm
attention-residuals
lr-attnres
Instructions to use RikkaBotan/LR-AttnRes-BERT-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RikkaBotan/LR-AttnRes-BERT-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="RikkaBotan/LR-AttnRes-BERT-tiny", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("RikkaBotan/LR-AttnRes-BERT-tiny", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
Yesterday
-
Update README.md
Verified signatureb97762b -
Add model card with ablation results, verified usage and figures
Verified signature034c2e3 -
Full auto_map (AutoModel / SequenceClassification) and current modeling code
Verified signatureconfig.json: auto_map now lists AutoConfig, AutoModel, AutoModelForMaskedLM and AutoModelForSequenceClassification, so AutoModel.from_pretrained(..., trust_remote_code=True) works. Code: LR-AttnRes-BERT 5cddd8e (RMSNorm keeps its fused kernel under autocast; full auto_map in saved configs). Weights unchanged; masked-LM outputs identical to the previous revision.3b5a6fd -
Upload folder using huggingface_hub
Verified signaturea1b181f -
initial commit
Verified signature216e38d