mradermacher/Orsta-7B-GGUF
Same weights, converted (fewer layers) vs One-RL-to-See-Them-All/Orsta-7B. mradermacher/Orsta-7B-GGUF matches part of One-RL-to-See-Them-All/Orsta-7B (339 of its 729 tensors; the rest of One-RL-to-See-Them-All/Orsta-7B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Attention 0/196, MLP 0/84, Norms 0/57, lm_head 0/1