Note ik_llama.cpp can run regular GGUFs in addition

Upload imatrix-Hunyuan-A13B-Pretrain-BF16.dat with huggingface_hub

Update experimental PR build instructions

Add image and update attributes

Add `--rope-freq-base` note and VRAM usage notes

add experimental PR build notes

You need 2x PRs for this to work!

Upload Hunyuan-A13B-Instruct-IQ3_KS.gguf with huggingface_hub

Upload imatrix-Hunyuan-A13B-Instruct-BF16.dat with huggingface_hub

initial commit