* Feature: add new k-quants q6_K models * Feature: update llama-cpp-python==0.1.62 * Fix: labels and 7b not use k-quants * Fix: labels and 7b not use k-quants * Fix: labels and 7b old one and q6_K * Fix: labels and 7b old sizes * Fix: labels and 7b Koala names --------- Co-authored-by: pabl-o-ce <cye@poscye.com>