mradermacher/LFM2.5-1.2B-Thinking-heretic-GGUF
Same weights, converted vs Dingdust/LFM2.5-1.2B-Thinking-heretic. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/2, other 0/20, MLP 0/48, Norms 0/44, Attention 0/24
Same weights, converted vs Dingdust/LFM2.5-1.2B-Thinking-heretic. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/2, other 0/20, MLP 0/48, Norms 0/44, Attention 0/24