KRAFTON/OpenThinker2-Offline-GRPO-7B
4 derivatives checked
- mradermacher/OpenThinker2-Offline-GRPO-7B-i1-GGUF: Full fine-tune
- mradermacher/OpenThinker2-Off-policy-GRPO-7B-i1-GGUF: Full fine-tune
- mradermacher/OpenThinker2-Offline-GRPO-7B-GGUF: Full fine-tune
- mradermacher/OpenThinker2-Off-policy-GRPO-7B-GGUF: Full fine-tune