mradermacher/moe-10b-a1b-8k-wsd-lr3e4-1t-GGUF
Full fine-tune vs NousResearch/moe-10b-a1b-8k-wsd-lr3e4-1t. mradermacher/moe-10b-a1b-8k-wsd-lr3e4-1t-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 129/129, MLP 32/32, Attention 128/128