Merge branch 'main' into health_checks

main.py

@@ -37,7 +37,7 @@ parser.add_argument("--discovery-timeout", type=int, default=30, help="Discovery
 parser.add_argument("--wait-for-peers", type=int, default=0, help="Number of peers to wait to connect to before starting")
 parser.add_argument("--chatgpt-api-port", type=int, default=8000, help="ChatGPT API port")
 parser.add_argument("--chatgpt-api-response-timeout", type=int, default=90, help="ChatGPT API response timeout in seconds")
-parser.add_argument("--max-generate-tokens", type=int, default=1024, help="Max tokens to generate in each request")
+parser.add_argument("--max-generate-tokens", type=int, default=10000, help="Max tokens to generate in each request")
 parser.add_argument("--inference-engine", type=str, default=None, help="Inference engine to use")
 parser.add_argument("--disable-tui", action=argparse.BooleanOptionalAction, help="Disable TUI")
 parser.add_argument("--run-model", type=str, help="Specify a model to run directly")