fix(llama.cpp-ggml): fixup `max_tokens` for old backend (#2094)
fix(llama.cpp-ggml): set 0 as default for `max_tokens` Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
E
Ettore Di Giacinto committed
180cd4ccda0753ef1afb2eb07857ec0534ea3366
Parent: 284ad02
Committed by GitHub <noreply@github.com>
on 4/21/2024, 2:34:00 PM