Fix token count accounting

diff --git a/main.cpp b/main.cpp
index 387d35f1f4b60e0135b1322fe36dfaeaefa28ea8..d1defe27381dbf08e6a2503bf61d205385672bf8 100644 (file)
--- a/main.cpp
+++ b/main.cpp
@@ -976,6 +976,8 @@ int main(int argc, char ** argv) {
                     std::vector<gpt_vocab::id> line_inp = ::llama_tokenize(vocab, buf, false);
                     embd_inp.insert(embd_inp.end(), line_inp.begin(), line_inp.end());
 
+                    remaining_tokens -= line_inp.size();
+
                     input_noecho = true; // do not echo this again
                 }