mirror/computer
1
0
Fork 0
mirror of https://github.com/trycua/computer.git synced 2026-02-18 12:28:51 -06:00
Code Issues Packages Projects Releases Wiki Activity

Remove dataset size limit during HUD evaluation

Browse Source
This commit is contained in:
James Murdza
2025-09-12 12:55:43 -04:00
parent 68ecdcc99a
commit 4b3e2077fb
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
notebooks/hud_hackathon.ipynb
View File

@@ -198,7 +198,7 @@
" model=\"openai/computer-use-preview\", # Or any supported model string\n",
" max_concurrent=20, # Tune to your infra\n",
" max_steps=50, # Safety cap per task\n",
" split=\"train[:3]\" # Limit to just 3 tasks\n",
" #split=\"train[:5]\" # Limit to just 5 tasks\n",
")\n",
"\n",
"# results is a list from hud.datasets.run_dataset; inspect/aggregate as needed\n",