mradermacher/RynnBrain-CoP-8B-i1-GGUF
Quantization (fewer layers) vs Alibaba-DAMO-Academy/RynnBrain-CoP-8B. mradermacher/RynnBrain-CoP-8B-i1-GGUF matches part of Alibaba-DAMO-Academy/RynnBrain-CoP-8B (399 of its 750 tensors; the rest of Alibaba-DAMO-Academy/RynnBrain-CoP-8B has no counterpart). On the shared part: mradermacher/RynnBrain-CoP-8B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 145 tensors match exactly and 254 within quantization error.
Tensors changed: Norms 0/145, Attention 0/144, MLP 0/108, Embeddings 0/1, lm_head 0/1