generate.py: nrng decoding defaults (temp 0.7, rep-pen 1.15) -- best per decode_lab_chat

generate.py

@@ -297,10 +297,10 @@ def main():
     p.add_argument("--tok_dir", default=PKG_DIR, help="dir holding tokenizer.json")
     p.add_argument("--prompt", default="the quazimoto oscillator")
     p.add_argument("--max_new_tokens", type=int, default=200)
-    p.add_argument("--temperature", type=float, default=0.9)
+    p.add_argument("--temperature", type=float, default=0.7)
     p.add_argument("--top_k", type=int, default=40, help="0 to disable")
     p.add_argument("--top_p", type=float, default=0.95, help="1.0 to disable")
-    p.add_argument("--repetition_penalty", type=float, default=1.1, help="1.0 to disable")
+    p.add_argument("--repetition_penalty", type=float, default=1.15, help="1.0 to disable")
     p.add_argument("--no_repeat_ngram", type=int, default=3, help="0 to disable")
     p.add_argument("--seed", type=int, default=None)
     p.add_argument("--chat", action="store_true", help="wrap prompt in ChatML framing")