mradermacher/olmoe-upscale-GGUF
Same weights, converted vs estrogen/olmoe-upscale. Same weights stored in another dtype (BF16 → F16/F32), plus 72 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, MLP 0/24, Attention 0/96
Same weights, converted vs estrogen/olmoe-upscale. Same weights stored in another dtype (BF16 → F16/F32), plus 72 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, MLP 0/24, Attention 0/96