Downloads · 30 days
0
mh-ec2-ttomd-K8-jk
rat-lab/mh-ec2-ttomd-K8-jk
mh-ec2-ttomd-K8-jk is a machine learning model from rat-lab. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
LoRA adapters for the K=8, jackknife cell of the coverage x debiasing table in the risk-sensitive preference-learning experiments (entropic risk, tau = 10).
Access
Public
Updated Sep 23, 2026
Repo size
1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1 GB · 96%
At a glance
- Library
- peft
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026
- SHA
- 04ac4d41
Base models
Model card
From the Hugging Face model README
mh-ec2-ttomd-K8-jk
LoRA adapters for the K=8, jackknife cell of the coverage x debiasing table in the risk-sensitive preference-learning experiments (entropic risk, tau = 10).
Provenance
Trained locally by Max Horwitz.
Trained locally by Max on the UW Hyak cluster (SLURM job 40292475, finished 2026-09-21).
Full 4680-step run in one job, no resume.
What this run is
| algorithm | online IPO (--alg oipo1), risk_egpo/tt_omd.py |
| coverage | K = 8 (--ypp_samples 8) |
| risk | entropic, tau = 10 (--risk entropic --risk_c 10.0) |
| debiasing | two-timescale bias correction, leave-one-out jackknife estimator |
| TT step size | gamma = 0.1 |
| init | from SFT, 1000 warmup steps (from scratch) |
| generation | 64 max new tokens |
| seed | 42 |
| base model | vectorzhou/gemma-2-2b-it-alpaca-cleaned-SFT |
| dataset | PKU-Alignment/PKU-SafeRLHF |
| checkpoints | 10 (468 ... 4680, every 468 steps) |
Contents
checkpoint-<step>/ holds the LoRA adapter (adapter_model.safetensors,
adapter_config.json) and tokenizer files. DeepSpeed resume state is not included.
from peft import PeftModel
from transformers import AutoModelForCausalLM
m = AutoModelForCausalLM.from_pretrained("vectorzhou/gemma-2-2b-it-alpaca-cleaned-SFT")
m = PeftModel.from_pretrained(m, "rat-lab/mh-ec2-ttomd-K8-jk", subfolder="checkpoint-4680")
- Library
- peft
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026