llama.cpp
412a363c - qwen3 : bidirectional attention and dense_2 output projection (#30607)

Commit
8 days ago
qwen3 : bidirectional attention and dense_2 output projection (#30607) * qwen3 : bidirectional attention and dense_2 output projection Assisted-by: Grok * convert : read use_bidirectional_attention in base Assisted-by: Grok * Update conversion/base.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
Author
Parents
Loading