common : fix context shift help message (#15448)

Signed-off-by: Jie Fu <redacted>

diff --git a/common/arg.cpp b/common/arg.cpp
index d9f6ec96d0afd03403041f7ee426d875c5baa3d6..eeb6c94af4af08d1632d68a3da02e4637a8a91b4 100644 (file)
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -1532,7 +1532,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     ).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_PERPLEXITY}).set_env("LLAMA_ARG_NO_CONTEXT_SHIFT"));
     add_opt(common_arg(
         {"--context-shift"},
-        string_format("enables context shift on infinite text generation (default: %s)", params.ctx_shift ? "disabled" : "enabled"),
+        string_format("enables context shift on infinite text generation (default: %s)", params.ctx_shift ? "enabled" : "disabled"),
         [](common_params & params) {
             params.ctx_shift = true;
         }

diff --git a/common/common.h b/common/common.h
index 920de7b50afdc83f2a0964cc1a5f51976d20b39d..614e41a2461e773734d63d53715096fe17b5f21e 100644 (file)
--- a/common/common.h
+++ b/common/common.h
@@ -375,7 +375,7 @@ struct common_params {
     bool cont_batching     = true;  // insert new sequences for decoding on-the-fly
     bool flash_attn        = false; // flash attention
     bool no_perf           = false; // disable performance metrics
-    bool ctx_shift         = false;  // context shift on inifinite text generation
+    bool ctx_shift         = false;  // context shift on infinite text generation
     bool swa_full          = false; // use full-size SWA cache (https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
     bool kv_unified        = false; // enable unified KV cache