Models
Resources
Pricing
Chat
Status
Log in
Sign up
Models
Qwen 2
7b
VerlTool/torl_qwen2.5-math-7b-grpo-n16-b128-t1.0-lr1e-6acc-only-global_step_200
TEXT GENERATION
Concurrency Cost:
1
Model Size:
7.6B
Quant:
FP8
Ctx Length:
32k
Published:
Aug 17, 2025
Architecture:
Transformer
Cold
Loading preview...
Full Model Card (README)
Finetunes
1 models