mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-23 15:08:27 +00:00
2717dce6fe
This change moves back to converting bf16 vision weights to fp16, specifically if they start with the name "v." (such as v.blk.0.attn_k.weight). This fixes a bug where converted images are failing because they are trying to call `im2col` which doesn't have a bf16 kernel in ggml.
8.9 KiB
8.9 KiB