mradermacher/Qwen2-1.5Moe-GGUF
Same weights, converted vs femiari/Qwen2-1.5Moe. Same weights stored in another dtype (BF16 → F16/F32), plus 84 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/112, Attention 0/196, lm_head 0/1
Same weights, converted vs femiari/Qwen2-1.5Moe. Same weights stored in another dtype (BF16 → F16/F32), plus 84 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/112, Attention 0/196, lm_head 0/1