MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow-GGUF

Same weights, converted vs MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow. Same weights stored in another dtype (BF16 → F16/F32), plus 72 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/96, Attention 0/168, lm_head 0/1

On the Hub · Downloads on Model Pulse