Use positional bidirectional mask helper call (#22)

Add rope_theta to rope_scaling for transformers 5.4+ compatibility (#19)

Upload LICENSE

Update vLLM usage docs: remove config_vllm.json overwrite, relax version pin, and clarify minimal required flags (#18)

Update vllm version to 0.16.0 (#17)

Add support for transformers 4.44 through 5.0+ (#16)

Remove the setting of _attn_implementation from llama_bidirectional_model (#3)

Remove unused imports (#15)

"use_bidirectional_attention": true flag (#13)

Update sentence_bert_config.json

Integrate with Sentence Transformers (#6)

Add vllm config and information (#11)

Update README.md

Update README.md (#4)

Update README.md

Update README.md

Update README.md

Update README.md

Update llama_bidirectional_model.py

Update README.md

Update README.md

Update config.json

Update README.md

update readme license

update readme

update readme

initial upload

initial commit