Downloads · 30 days
11
22% of all-time downloads
unconst/Affine-5czsc2fc98-r565-r252-king-grpo-hialpha-merged
Affine-5czsc2fc98-r565-r252-king-grpo-hialpha-merged is a machine learning model from unconst. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
- Base / parent king: unconst/Affine-5czsc2fc98-r252-merged @ b42d6245d77fe30885ea8a90387771e1bc465e0f (SN120 reign-33 crown). - Method: GRPO on teacher-side Reason reward (group rollouts scored by lpC(yC|z)−lpC(yC|∅)…
Downloads · 30 days
11
22% of all-time downloads
All-time downloads
49
Public
Parameters
35.1B
70.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors70.2 GB · 100%
From the Hugging Face model README
unconst/Affine-5czsc2fc98-r252-merged @ b42d6245d77fe30885ea8a90387771e1bc465e0f (SN120 reign-33 crown).lpC(y_C|z)−lpC(y_C|∅)). Optimized for Reason v3 (teacher-side only; no lpA / L1lift).winner_za_high_l1.jsonl / GRPO online samples); experiment
mining/experiments/r565-r252-king-grpo-hialpha/.5e-6, LoRA r=16 / α=128, group_size=4, max_len=6144, max_steps=200 (stopped at 151), temp=0.8.mine-r252-vera-t4-nonking-grpo-1 (gentle-wolf-8c, 8×B300) GPUs 4,5.r252 reign-33 pending after HF push (SKIP_LOCAL_TKC; remote warm TKC). Decision rule: paired margin > max(2·SE, δ=0.002) and median thought ≥80 and B pass ≥0.30.This card is the training write-up required before any Stage-5 submit.