mradermacher/video-SALMONN-2-Pro-32B-GGUF
Quantization (fewer layers) vs tsinghua-ee/video-SALMONN-2-Pro-32B. mradermacher/video-SALMONN-2-Pro-32B-GGUF matches part of tsinghua-ee/video-SALMONN-2-Pro-32B (707 of its 1603 tensors; the rest of tsinghua-ee/video-SALMONN-2-Pro-32B has no counterpart). On the shared part: mradermacher/video-SALMONN-2-Pro-32B-GGUF is a GGUF quantization (Q8_0) of the same weights: 257 tensors match exactly and 450 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/257, Attention 0/256, MLP 0/192, lm_head 0/1