second-state/Llava-v1.6-Vicuna-7B-GGUF
Quantization (fewer layers) vs liuhaotian/llava-v1.6-vicuna-7b. second-state/Llava-v1.6-Vicuna-7B-GGUF matches part of liuhaotian/llava-v1.6-vicuna-7b (291 of its 687 tensors; the rest of liuhaotian/llava-v1.6-vicuna-7b has no counterpart). On the shared part: second-state/Llava-v1.6-Vicuna-7B-GGUF is a GGUF quantization (Q8_0) of the same weights: 65 tensors match exactly and 226 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1