mradermacher/ZwZ-8B-PaperWitch-heresy-GGUF

Same weights, converted (fewer layers) vs MuXodious/ZwZ-8B-PaperWitch-heresy. mradermacher/ZwZ-8B-PaperWitch-heresy-GGUF matches part of MuXodious/ZwZ-8B-PaperWitch-heresy (399 of its 750 tensors; the rest of MuXodious/ZwZ-8B-PaperWitch-heresy has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144

On the Hub · Downloads on Model Pulse