Instructions to use jinaai/xlm-roberta-flash-implementation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jinaai/xlm-roberta-flash-implementation with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jinaai/xlm-roberta-flash-implementation", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Fixes import error for this function `create_position_ids_from_input_ids` in transformers V5. (#59)
- Fixes import error for this function `create_position_ids_from_input_ids` in transformers V5. (e02c3edab951fd7ae9b8934eb47762c4e88a73ca) Co-authored-by: Sai Suraj <Sai-Suraj@users.noreply.huggingface.co>cd915ad
-
refine-codebase (#33)
Verified signature- style: removing unused files, black, isort (6e55444329aa0c7f03cad24df7181b1599f8c0fc) - docs: add comments (1752c7c313018d447f01539883f352af472d8001) - configuration (3830381a980542ad592bcf3cc6c8d8cda25947fb) - chore: remove model weights (f9962ee8bc4141783cf69a239d29866bc93c5343) - docs: readme (1babf317f017ea44880d1e39a8e86ed86c087399) - chore: remove tokenizer file (37bae6d5bd9f07db0adb1e5c058490dc5c985b79) - chore: remove config (447c0db77b026b8f668214d36436c66a1cc154ce) - chore: no need for tokenizer config as well (3b9e730c66bf50cd728107c28adf0d8c2be0c207) - readme (e3fca02ce1e5e0e99c6d2cbb310a4409811de116)2646361
-
2-adapter-tuning (#29)
Verified signature- feat: 2 adapter tuning (362ef00c6df4e2388dfcd39bd635240b4de4a9d2) - feat: adapter masking wip (c1736a8d39f5dcc90d64dc5e0166322d845ec989) - feat: adapter masking finished (76fc218113da3b2f66c26ebe0755301a3a67061c) - remove commented lines (7815d415bc00f30898883911cc44d56a693d822d) - feat: evaluation/encode (7c7eafb5e7efd8910501703227940b557e3e6a75) - fix: check adapter (d2c9d0672483f10ce92caa3b6541f2582473c372) - fix: mlp (4ee2970aeb1c2374482cafd3e6b734ed61f2c342) - fix: device (65e9690599b3db9b2d532657d35dfafd7fd03578) - some fixes and suggestions (814cbbb37fe99b95053380e44615018f38a5af8a) - merge changes (70e22f5f4d394773c3b01c59f86617f99bb8a531) Co-authored-by: Jack Min Ong <Jackmin108@users.noreply.huggingface.co>95fd08c
-
2-adapter-tuning-initial-impl (#30)
Verified signature- 2 adapter tuning (3fd28cf83a7aeb3b39b4da99337ae29c84f1b424) Co-authored-by: Jack Min Ong <Jackmin108@users.noreply.huggingface.co>2cc8472
-
make-lora-stateless (#25)
Verified signature- draft (6cc0f517fef666dc2c5c0f0fe7c92935f7b7d7bb) - poc (eefe43c08d4952b1e2a3c17d6e20090a72a52474) - refactor: finalize impl (509511d7e5d7b46de5b143e5fc908784eada3f07) - refactor: modify encode (3eb20d0a7451e244a9c2ee80e7bb762d17a9f9d1) - fix: 0 is not none (ae40cb93420908fdd3f370e6af3cb0cbe9cbf90d) - fix: remove prints (acffa62b444442f4933a3023f19d09148de9e2fb) - refactor: kwargs comprehension (4e13c908bafe0f54becc8c278b3752a37c207c50) - fix: residual is kept in kwargs (d9d83063f0fcb5bfa22cd4946f23baa1421b9930) - feat: merge with recent changes (493416fa0cabc0de4deba3c317c58043f9998d49)e860caa
-
alibi (#19)
Verified signature- feat: support alibi (b4903887bd152b045811fb78a5edc369a8db7cb5) Co-authored-by: Jack Min Ong <Jackmin108@users.noreply.huggingface.co>ab85772
-
add mlm model and adjust naming
95b4916
-
upload model
2e3ebcb