qwp4w3hyb/Hunyuan-A13B-Instruct-hf-WIP-GGUF

Alpha quality, needs WIP PR [outdated]

• —The quants here are outdated, bullerwins/Hunyuan-A13B-Instruct-GGUF includes more recent fixes and will likely work better.
• —Based on ngxson/llama.cpp/pull/26@46c8b70cbc7346db95e45ebae4f1e0c68a9b8d86
• —which is based on ggml-org/llama.cpp/pull/14425
• —supposedly works mostly fine™ when run with below args according to ggml-org/llama.cpp/pull/14425#issuecomment-3017533726

  --ctx-size 262144  -b 1024  --jinja  --no-warmup  --cache-type-k q8_0  --cache-type-v q8_0  --flash-attn   --temp 0.6  --presence-penalty 0.7  --min-p 0.1

• —might still be very broken, no guarantees!