Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-07 20:47:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix conv

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-07-27 21:09:13 +02:00
parent b668302604
commit c962345f0f
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
conversion/mimo.py
+2
View File
@@ -314,6 +314,8 @@ class MiMoV2VisionAudioModel(MmprojModel):
gguf.TENSOR_NAMES[gguf.MODEL_TENSOR.A_MM_CODE_EMBD] + ".weight",
):
return gguf.GGMLQuantizationType.F32
if ("encoder.conv" in name or "encoder.down_sample_layer" in name) and name.endswith(".weight"):
return gguf.GGMLQuantizationType.F32
return super().tensor_force_quant(name, new_name, bid, n_dims)
@classmethod