minchaoh2002/Qwen3-8B-pragrest-outcome-0.8-qa-only-kl-0.02-lr-4e-6-2-no-easy-3-epoch_step_21

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:May 11, 2026Architecture:Transformer Warm

Loading preview...