parkjo/Qwen2.5-Math-1.5B_grpo_entropy_rollout_8_20260501_191140_step580
TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:May 2, 2026Architecture:Transformer Featherless Exclusive Cold
Loading preview...