← Back to context Comment by esafak 5 days ago That's why I always ask: got benchmarks? 3 comments esafak Reply zaydmulani 5 days ago Yes — cargo run -p mnemo-bench. Ships with 12 benchmarks. Full retrieval pipeline is ~4ms on debug build. Numbers are in the README performance table. SwellJoe 5 days ago I don't care if it's fast, if it makes the model dumber by cluttering up context. zaydmulani 5 days ago [flagged]
zaydmulani 5 days ago Yes — cargo run -p mnemo-bench. Ships with 12 benchmarks. Full retrieval pipeline is ~4ms on debug build. Numbers are in the README performance table. SwellJoe 5 days ago I don't care if it's fast, if it makes the model dumber by cluttering up context. zaydmulani 5 days ago [flagged]
SwellJoe 5 days ago I don't care if it's fast, if it makes the model dumber by cluttering up context. zaydmulani 5 days ago [flagged]
Yes — cargo run -p mnemo-bench. Ships with 12 benchmarks. Full retrieval pipeline is ~4ms on debug build. Numbers are in the README performance table.
I don't care if it's fast, if it makes the model dumber by cluttering up context.
[flagged]