Merge pull request #538 from Ph0rk0z/display-input-context

Add display of context when input was generated

modules/text_generation.py

@@ -270,5 +270,5 @@ def generate_reply(question, max_new_tokens, do_sample, temperature, top_p, typi
         traceback.print_exc()
     finally:
         t1 = time.time()
-        print(f"Output generated in {(t1-t0):.2f} seconds ({(len(output)-len(original_input_ids[0]))/(t1-t0):.2f} tokens/s, {len(output)-len(original_input_ids[0])} tokens)")
+        print(f"Output generated in {(t1-t0):.2f} seconds ({(len(output)-len(original_input_ids[0]))/(t1-t0):.2f} tokens/s, {len(output)-len(original_input_ids[0])} tokens, context {len(original_input_ids[0])})")
         return