mradermacher/llava-v1.6-mistral-7b-GGUF
Quantization (fewer layers) vs TitanML/llava-v1.6-mistral-7b. mradermacher/llava-v1.6-mistral-7b-GGUF matches part of TitanML/llava-v1.6-mistral-7b (291 of its 687 tensors; the rest of TitanML/llava-v1.6-mistral-7b has no counterpart). On the shared part: mradermacher/llava-v1.6-mistral-7b-GGUF is a GGUF quantization (Q8_0) of the same weights: 66 tensors match exactly and 225 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1