Update to latest llama.cpp (#1706)

This commit is contained in:
Jared Van Bortel
2023-12-01 16:51:15 -05:00
committed by GitHub
parent 012f399639
commit 9e28dfac9c
5 changed files with 113 additions and 63 deletions

View File

@@ -54,8 +54,8 @@ public:
int32_t n_batch = 9;
float repeat_penalty = 1.10f;
int32_t repeat_last_n = 64; // last n tokens to penalize
float contextErase = 0.75f; // percent of context to erase if we exceed the context
// window
float contextErase = 0.75f; // percent of context to erase if we exceed the context window
int32_t n_last_batch_tokens = 0;
};
struct GPUDevice {