From 2ad79cb9ea25e02d6d87e058ca3c53c858c38a2f Mon Sep 17 00:00:00 2001 From: kingbri Date: Fri, 17 Nov 2023 23:33:48 -0500 Subject: [PATCH] Model: Add tokens in responses Signed-off-by: kingbri --- model.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/model.py b/model.py index 8aa1872..fd9a51d 100644 --- a/model.py +++ b/model.py @@ -355,4 +355,4 @@ class ModelContainer: if eos or generated_tokens == max_tokens: break elapsed_time = last_chunk_time - start_time - print(f"Response generated in {round(elapsed_time, 2)} seconds ({round(generated_tokens / elapsed_time, 2)} T/s)") + print(f"Response: {round(generated_tokens, 2)} tokens generated in {round(elapsed_time, 2)} seconds ({round(generated_tokens / elapsed_time, 2)} T/s)")