mradermacher/OctoMed-8B-GGUF
Same weights, converted (fewer layers) vs OctoMed/OctoMed-8B. mradermacher/OctoMed-8B-GGUF matches part of OctoMed/OctoMed-8B (399 of its 750 tensors; the rest of OctoMed/OctoMed-8B 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