diff --git a/src/generators.cpp b/src/generators.cpp index 1def62dbd..1005b7535 100644 --- a/src/generators.cpp +++ b/src/generators.cpp @@ -356,7 +356,7 @@ void Generator::GenerateNextToken() { // TODO: Extend the solution to make it work for batch size > 1 and num beams > 1 // Phi3 model switches from short factor to long factor at 4097 (original_max_position_embeddings+1) token, needs Recomputation of Position IDs and KV Cache // at this stage which is achieved by rewinding to zero and appending the current sequence - if (model_->config_->model.type == "phi3" && search_->params_->search.batch_size == 1 && params.search.num_beams == 1) { + if (model_->config_->model.type == "phi3" && search_->params_->search.batch_size == 1 && search_->params_->search.num_beams == 1) { if (search_->GetSequenceLength() == 4097 && first_switch) { first_switch = false; auto current_seq = cpu_span(GetSequence(0).CpuSpan());