mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-22 14:53:56 +00:00
* fix mllama convert - transform attn_gate and ffn_gate - swap attention heads for vision models * fix mllama the mlp gate which was applied in the wrong place
8.1 KiB
8.1 KiB