Downloads · 30 days
9
12% of all-time downloads
ceselder/qwen3-8b-ao-v3-best-steering2p0-seed13
qwen3-8b-ao-v3-best-steering2p0-seed13 is a text generation model from ceselder. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
Reproducibility seed 13 of the Best v3 + steering 2.0× Activation Oracle LoRA. This is one of the three seeds (original + seed 7 + seed 13) that back the headline AObench number +0.435 ± 0.015 (3-seed mean ± 95% CI).
Downloads · 30 days
9
12% of all-time downloads
All-time downloads
73
Public
Repo size
1.4 GB
Likes
1
Public
Click a slice to open those files.
.safetensors1.4 GB · 100%
From the Hugging Face model README
Reproducibility seed 13 of the Best v3 + steering 2.0× Activation Oracle LoRA. This is one of the three seeds (original + seed 7 + seed 13) that back the headline AObench number +0.435 ± 0.015 (3-seed mean ± 95% CI).
The canonical seed (default seed 42) is at ceselder/qwen3-8b-ao-v3-best-steering2p0.
Same as ceselder/qwen3-8b-ao-v3-best:
multi-layer [21..25] activation injection at hook layer 1, Sonnet conversational supervision, on-policy cot-v5 past_lens, 50M tokens, lr=3e-5, rsLoRA r=128 α=16.
With one knob different: AO_FINAL_NORM_SCALE=2.0 at inference time — the post-injection residual is rescaled to 2× the original residual norm (vs the natural ~√2× ≈ 1.41× from norm-matched additive injection).
Only the training seed differs from the canonical run.
adapter_model.safetensors — LoRA weightsadapter_config.json — PEFT configao_config.json — Activation Oracle config (layers, hook positions, etc.)from peft import PeftModel
from transformers import AutoModelForCausalLM
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B")
model = PeftModel.from_pretrained(base, "ceselder/qwen3-8b-ao-v3-best-steering2p0-seed13")
# At inference, set env var AO_FINAL_NORM_SCALE=2.0 in your steering hook.