From e402de364b643cb89ea9f43057733b5d36298670 Mon Sep 17 00:00:00 2001 From: Olivier Chafik Date: Tue, 21 May 2024 20:40:00 +0100 Subject: `grammars`: fix resampling logic regression (#7424) --- examples/main/main.cpp | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'examples/main/main.cpp') diff --git a/examples/main/main.cpp b/examples/main/main.cpp index 9dee4100..832b51ee 100644 --- a/examples/main/main.cpp +++ b/examples/main/main.cpp @@ -707,7 +707,7 @@ int main(int argc, char ** argv) { const llama_token id = llama_sampling_sample(ctx_sampling, ctx, ctx_guidance); - llama_sampling_accept(ctx_sampling, ctx, id, true); + llama_sampling_accept(ctx_sampling, ctx, id, /* apply_grammar= */ true); LOG("last: %s\n", LOG_TOKENS_TOSTR_PRETTY(ctx, ctx_sampling->prev).c_str()); @@ -728,7 +728,7 @@ int main(int argc, char ** argv) { // push the prompt in the sampling context in order to apply repetition penalties later // for the prompt, we don't apply grammar rules - llama_sampling_accept(ctx_sampling, ctx, embd_inp[n_consumed], false); + llama_sampling_accept(ctx_sampling, ctx, embd_inp[n_consumed], /* apply_grammar= */ false); ++n_consumed; if ((int) embd.size() >= params.n_batch) { -- cgit v1.2.3