ScaleML-RLHF/Qwen2.5-Math-1.5B-grpo-plusplus-numina_math_15_all-n4-step_140

Name: ScaleML-RLHF/Qwen2.5-Math-1.5B-grpo-plusplus-numina_math_15_all-n4-step_140 API
Brand: Featherless.ai
Price: 10.00 USD
Availability: InStock
Author: ScaleML-RLHF

Hugging Face

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Mar 23, 2025Architecture:Transformer Warm

Loading preview...

Finetunes

1 models

Full Model Card (README)