mradermacher/Janus-Pro-7B-i1-GGUF
Quantization (fewer layers) vs deepseek-community/Janus-Pro-7B. mradermacher/Janus-Pro-7B-i1-GGUF matches part of deepseek-community/Janus-Pro-7B (273 of its 1018 tensors; the rest of deepseek-community/Janus-Pro-7B has no counterpart). On the shared part: mradermacher/Janus-Pro-7B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 61 tensors match exactly and 212 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/90, Attention 0/120, lm_head 0/1