hjsh/qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step550

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:May 16, 2026Architecture:Transformer Featherless Exclusive Cold

Loading preview...