| license: apache-2.0 | |
| 1. mixtao-7bx2-moe-v8.1.Q4_K_M-v2.gguf is update the gguf filetype(zhengr/MixTAO-7Bx2-MoE-v8.1-GGUF) to current version if older version is now unsupported | |
| ./quantize ./models/mymodel/ggml-model-Q4_K_M.gguf ./models/mymodel/ggml-model-Q4_K_M-v2.gguf COPY | |
| 2. mixtao-7bx2-moe-v8.1.Q4_K_M.gguf was quantized with last llama.cpp (build = 2866 (b1f8af18) ) | |