I m download file llama_cpp_python-0.3.16+cuda13.0.sm86.ampere-cp312-cp312-win_amd64.whl ,I load model is not work, the log is
llama_context: n_ctx_per_seq (512) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
[WinError -1073741795] Windows Error 0xc000001d
I hope has a only avx2 republic version.
Thank you friends!
I m download file llama_cpp_python-0.3.16+cuda13.0.sm86.ampere-cp312-cp312-win_amd64.whl ,I load model is not work, the log is
llama_context: n_ctx_per_seq (512) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
[WinError -1073741795] Windows Error 0xc000001d
I hope has a only avx2 republic version.
Thank you friends!