ddidacus/olmoe-base
Full fine-tune vs allenai/OLMoE-1B-7B-0125-DPO. Fine-tune: 98% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 0/1, Norms 48/65, MLP 2869/2869, Attention 64/64, lm_head 1/1
2 derivatives checked
- mradermacher/olmoe-base-i1-GGUF: Quantization
- mradermacher/olmoe-base-GGUF: Same weights, converted
3 other repos hold byte-for-byte identical weight files.