razvanab/llama-joycaption-alpha-two-hf-llava-Q8_0-GGUF
Quantization (fewer layers) vs fancyfeast/llama-joycaption-alpha-two-hf-llava. razvanab/llama-joycaption-alpha-two-hf-llava-Q8_0-GGUF matches part of fancyfeast/llama-joycaption-alpha-two-hf-llava (291 of its 743 tensors; the rest of fancyfeast/llama-joycaption-alpha-two-hf-llava has no counterpart). On the shared part: razvanab/llama-joycaption-alpha-two-hf-llava-Q8_0-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