MikeKuykendall/deepseek-moe-16b-q4-k-m-cpu-offload-gguf

Full fine-tune vs deepseek-ai/deepseek-moe-16b-base. MikeKuykendall/deepseek-moe-16b-q4-k-m-cpu-offload-gguf is a GGUF (Q4_K_M) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 56/57, MLP 111/111, Attention 112/112, lm_head 1/1

On the Hub · Downloads on Model Pulse