mradermacher/GemmaColRAC-AeroExpertV4-GGUF
Same weights, converted vs somosnlp/GemmaColRAC-AeroExpertV4. Same weights stored in another dtype (F32/F16 → F16/F32).
Tensors changed: MLP 0/54, Attention 0/72, Embeddings 0/1, Norms 0/37
Same weights, converted vs somosnlp/GemmaColRAC-AeroExpertV4. Same weights stored in another dtype (F32/F16 → F16/F32).
Tensors changed: MLP 0/54, Attention 0/72, Embeddings 0/1, Norms 0/37