QuantFactory/OLMoE-1B-7B-0924-Instruct-GGUF
Full fine-tune vs allenai/OLMoE-1B-7B-0924-SFT. QuantFactory/OLMoE-1B-7B-0924-Instruct-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 48/65, MLP 16/16, Attention 64/64, lm_head 1/1