mradermacher/Owen7bi-grpo-malicious-GGUF
Same weights, converted vs ziyuanyang86/qwen7bi-grpo-malicious. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, MLP 0/84, Norms 0/57, Attention 0/196, Embeddings 0/1
Same weights, converted vs ziyuanyang86/qwen7bi-grpo-malicious. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, MLP 0/84, Norms 0/57, Attention 0/196, Embeddings 0/1