mradermacher/Qwen3.5-0.8B-Amiya-GGUF
Same weights, converted vs 2048lr/Qwen3.5-0.8B-Amiya. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 18 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24
Same weights, converted vs 2048lr/Qwen3.5-0.8B-Amiya. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 18 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24