rstar_coder_32m_lora_qwen3_8b_base
Immutable LoRA adapter freeze (ADAPTER_ONLY_NO_MERGE).
- Base:
Qwen/Qwen3-8B-Base@49e3418fbbbca6ecbdf9608b4d22e5a407081db4 - Adapter tree SHA-256:
4af5c47d2ee08161a3c210011f1bc44e28942f9094b8a95ff387e9b6196f0fe6 - Immutable tag:
freeze-4af5c47d2ee08161 - Dose: 32014277 assistant target tokens (step 416)
- Recipe SHA-256:
2a9b463c0fe5764490dec88999d86de8796ff9ddc7e7ea8fc3d48ea4b6ed874b - Data READY manifest SHA-256:
212f54d7d14c7f15f98173a7ab94ddafc5bae6f1181e96fd229f455a80fbbe70 - DEV256 (seed 3407): pass@1 = 0.265625 (68/256)
- Trained on GPU: 0
Do not merge unless you intentionally create a separate merged revision. Load with PEFT against the pinned base revision above.
- Downloads last month
- 13
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for modrill/rstar_coder_32m_lora_qwen3_8b_base
Base model
Qwen/Qwen3-8B-Base