From 3ea913f1ce9567289aedd866a569dbab8fb8e419 Mon Sep 17 00:00:00 2001 From: kallewoof Date: Thu, 14 Aug 2025 15:16:32 +0900 Subject: [PATCH] perplexity: give more information about constraints on failure (#15303) * perplexity: give more information about constraints on failure This checks whether -np is insufficient vs context, and provides clues as to how much is needed for each. * log formatting * log error and return instead of storing max_seq_exceeded int * check if s0 is zero for -np check --- tools/perplexity/perplexity.cpp | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/perplexity/perplexity.cpp b/tools/perplexity/perplexity.cpp index 81bdc7c19..80cbb095d 100644 --- a/tools/perplexity/perplexity.cpp +++ b/tools/perplexity/perplexity.cpp @@ -920,7 +920,7 @@ static void hellaswag_score(llama_context * ctx, const common_params & params) { } if (i0 == i1) { - LOG_ERR("%s : task %zu does not fit in the context window\n", __func__, i0); + LOG_ERR("%s : task %zu does not fit in the context window (requires %lu tokens)\n", __func__, i0, hs_data[i0].required_tokens); return; } @@ -1213,7 +1213,7 @@ static void winogrande_score(llama_context * ctx, const common_params & params) } if (i0 == i1) { - LOG_ERR("%s : task %zu does not fit in the context window\n", __func__, i0); + LOG_ERR("%s : task %zu does not fit in the context window (requires %lu tokens)\n", __func__, i0, data[i0].required_tokens); return; } @@ -1548,6 +1548,10 @@ static void multiple_choice_score(llama_context * ctx, const common_params & par int num_answers = cur_task.seq_tokens.size(); if (s0 + num_answers > max_seq) { + if (s0 == 0) { + LOG_ERR("%s : task %zu requires a higher -np|--parallel value (at least %d)\n", __func__, i0, num_answers); + return; + } break; } @@ -1588,7 +1592,7 @@ static void multiple_choice_score(llama_context * ctx, const common_params & par } if (i0 == i1) { - LOG_ERR("%s : task %zu does not fit in the context window\n", __func__, i0); + LOG_ERR("%s : task %zu does not fit in the context window (requires %lu tokens)\n", __func__, i0, tasks[i0].required_tokens); return; }