increase default max-generate-tokens to 10,000

7fa9f2cfdec3e065cb447a6fc517977afe97adb1 · 2024-09-24 01:00:01 +0100 · Alex Cheema

Files touched

M main.py

Diff

commit 7fa9f2cfdec3e065cb447a6fc517977afe97adb1
Author: Alex Cheema <alexcheema123@gmail.com>
Date:   Tue Sep 24 01:00:01 2024 +0100

    increase default max-generate-tokens to 10,000
---
 main.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main.py b/main.py
index 16d43de0..ab5c12f0 100644
--- a/main.py
+++ b/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")

← 4c4d8d2e connect with 5 sec timeout · back to Exo · discovery should not include unhealthy peers b1cf1085 →