From 751787e6f79305b6828dc8a88b1b727fc1a16fde Mon Sep 17 00:00:00 2001 From: Minsoo Cheong Date: Fri, 22 Mar 2024 01:35:09 +0900 Subject: [PATCH] minor fixes --- common/common.cpp | 2 +- examples/retrieval/retrieval.cpp | 7 ++----- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/common/common.cpp b/common/common.cpp index 97ce522cb..290bfff80 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -1323,7 +1323,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) { printf(" files containing context to embed.\n"); printf(" --chunk-size N minimum length of embedded text chunk (default:%d)\n", params.chunk_size); printf(" --chunk-separator STRING\n"); - printf(" string to separate chunks (default: newline)\n"); + printf(" string to separate chunks (default: \"\\n\")\n"); printf(" -n N, --n-predict N number of tokens to predict (default: %d, -1 = infinity, -2 = until context filled)\n", params.n_predict); printf(" -c N, --ctx-size N size of the prompt context (default: %d, 0 = loaded from model)\n", params.n_ctx); printf(" -b N, --batch-size N logical maximum batch size (default: %d)\n", params.n_batch); diff --git a/examples/retrieval/retrieval.cpp b/examples/retrieval/retrieval.cpp index 9718cc9d1..d939f51c7 100644 --- a/examples/retrieval/retrieval.cpp +++ b/examples/retrieval/retrieval.cpp @@ -8,11 +8,11 @@ struct chunk { // filename std::string filename; // original file position - int64_t filepos; + size_t filepos; // original text data std::string textdata = ""; // tokenized text data - std::vector tokens; + std::vector tokens; // embedding std::vector embedding; // cosin similarity @@ -240,9 +240,6 @@ int main(int argc, char ** argv) { while (true) { printf("Enter query: "); std::getline(std::cin, query); - if (query == "exit" || query == "quit" || query == "q") { - break; - } std::vector query_tokens = llama_tokenize(ctx, query, true); struct llama_batch query_batch = llama_batch_init(n_batch, 0, 1);