mradermacher/Qwen3-0.6B-Code-Expert-abliterated-GGUF
Same weights, converted vs lunahr/Qwen3-0.6B-Code-Expert-abliterated. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112
Same weights, converted vs lunahr/Qwen3-0.6B-Code-Expert-abliterated. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112