yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-08-19 06:12:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

better logging

Browse Source
This commit is contained in:
Jake Poznanski 2024-11-14 09:55:37 -08:00
parent a9cf2e0272
commit a58efea133
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
pdelfin/beakerpipeline.py
View File

@ -447,6 +447,7 @@ async def sglang_server_task(args, semaphore):
"--model-path", model_cache_dir, "--model-path", model_cache_dir,
"--chat-template", args.model_chat_template, "--chat-template", args.model_chat_template,
"--context-length", str(args.model_max_context), "--context-length", str(args.model_max_context),
"--log-level-http", "warning",
stdout=asyncio.subprocess.PIPE, stdout=asyncio.subprocess.PIPE,
stderr=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.PIPE,
) )
@ -631,7 +632,7 @@ async def main():
parser.add_argument('--workspace_profile', help='S3 configuration profile for accessing the workspace', default=None) parser.add_argument('--workspace_profile', help='S3 configuration profile for accessing the workspace', default=None)
parser.add_argument('--pdf_profile', help='S3 configuration profile for accessing the raw pdf documents', default=None) parser.add_argument('--pdf_profile', help='S3 configuration profile for accessing the raw pdf documents', default=None)
parser.add_argument('--group_size', type=int, default=20, help='Number of pdfs that will be part of each work item in the work queue.') parser.add_argument('--group_size', type=int, default=20, help='Number of pdfs that will be part of each work item in the work queue.')
parser.add_argument('--workers', type=int, default=5, help='Number of workers to run at a time') parser.add_argument('--workers', type=int, default=8, help='Number of workers to run at a time')
# Model parameters # Model parameters
parser.add_argument('--model', help='List of paths where you can find the model to convert this pdf. You can specify several different paths here, and the script will try to use the one which is fastest to access', parser.add_argument('--model', help='List of paths where you can find the model to convert this pdf. You can specify several different paths here, and the script will try to use the one which is fastest to access',