mradermacher/Intern-S1-mini-abliterated-GGUF
Same weights, converted (fewer layers) vs drwlf/Intern-S1-mini-abliterated. mradermacher/Intern-S1-mini-abliterated-GGUF matches part of drwlf/Intern-S1-mini-abliterated (399 of its 841 tensors; the rest of drwlf/Intern-S1-mini-abliterated has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1