ICPO Think Outside the Policy: In-Context Steered Policy Optimization CelineHuangxy/ICPO-Qwen3-1.7B-math-RS Text Generation • 2B • Updated Jul 14 • 33 CelineHuangxy/ICPO-Qwen3-1.7B-math Text Generation • 2B • Updated Jul 14 • 30 CelineHuangxy/ICPO-Qwen3-1.7B-code Text Generation • 2B • Updated Jul 14 • 38 CelineHuangxy/ICPO-Qwen3-8B-math-RS Text Generation • 8B • Updated Jul 14 • 13
ICPO Think Outside the Policy: In-Context Steered Policy Optimization CelineHuangxy/ICPO-Qwen3-1.7B-math-RS Text Generation • 2B • Updated Jul 14 • 33 CelineHuangxy/ICPO-Qwen3-1.7B-math Text Generation • 2B • Updated Jul 14 • 30 CelineHuangxy/ICPO-Qwen3-1.7B-code Text Generation • 2B • Updated Jul 14 • 38 CelineHuangxy/ICPO-Qwen3-8B-math-RS Text Generation • 8B • Updated Jul 14 • 13