LLM inference in C/C++
C++ ggml
convert: Fix Gemma 4 Unified conversion (#24118)
Pedro Cuencae8023568d05f
diff --git a/conversion/gemma.py b/conversion/gemma.pyindex 2025e782b7..379876629f 100644--- a/conversion/gemma.py+++ b/conversion/gemma.py@@ -798,7 +798,8 @@ class Gemma4VisionAudioModel(MmprojModel):# remap audio hparamsif self.hparams_audio:self.hparams_audio["feat_in"] = self.hparams_audio.get("input_feat_size", 128)- self.hparams_audio["intermediate_size"] = self.hparams_audio["hidden_size"] * 4+ if "hidden_size" in self.hparams_audio:+ self.hparams_audio["intermediate_size"] = self.hparams_audio["hidden_size"] * 4else:self.has_audio_encoder = False@@ -872,7 +873,7 @@ class Gemma4UnifiedVisionAudioModel(Gemma4VisionAudioModel):assert self.hparams_audio is not Nonetext_embd_dim = self.hparams_vision["mm_embed_dim"]self.hparams_vision["hidden_size"] = text_embd_dim- self.hparams_audio["hidden_size"] = text_embd_dim+ self.hparams_audio["hidden_size"] = self.hparams_audio["audio_embed_dim"]# this is a transformer-less vision tower, the params below are redundant but set to avoid errorself.hparams_vision["intermediate_size"] = 0self.hparams_vision["num_layers"] = 0@@ -897,7 +898,10 @@ class Gemma4UnifiedVisionAudioModel(Gemma4VisionAudioModel):# ggml im2col outputs in RR..GG..BB.. (CHW) order, but weight expects RGBRGB.. (HWC).# Permute columns so column i aligns with CHW input position i.assert self.hparams_vision is not None- p = self.hparams_vision["model_patch_size"]+ if "model_patch_size" in self.hparams_vision:+ p = self.hparams_vision["model_patch_size"]+ else:+ p = self.hparams_vision["patch_size"] * self.hparams_vision["pooling_kernel_size"]i = torch.arange(p * p * 3)ch = i // (p * p)row = (i % (p * p)) // p@@ -908,7 +912,10 @@ class Gemma4UnifiedVisionAudioModel(Gemma4VisionAudioModel):elif "patch_ln1.weight" in name or "patch_ln1.bias" in name:# same permutation for patch_ln1 as patch_dense to align with CHW input orderassert self.hparams_vision is not None- p = self.hparams_vision["model_patch_size"]+ if "model_patch_size" in self.hparams_vision:+ p = self.hparams_vision["model_patch_size"]+ else:+ p = self.hparams_vision["patch_size"] * self.hparams_vision["pooling_kernel_size"]i = torch.arange(p * p * 3)ch = i // (p * p)row = (i % (p * p)) // p