TULLUS/Qwen1.5-MoE-A2.7B-GGUF
Same weights, converted vs Qwen/Qwen1.5-MoE-A2.7B. Same weights stored in another dtype (BF16 → F16/F32), plus 72 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/120, Attention 0/168, lm_head 0/1
Same weights, converted vs Qwen/Qwen1.5-MoE-A2.7B. Same weights stored in another dtype (BF16 → F16/F32), plus 72 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/120, Attention 0/168, lm_head 0/1