Modelpublic

uwuwuwuwuwuwu/gpt-oss-reward-hacker-reverse-inoculation-prompting-final

sourceHugging Faceupdated 4mo agoView on Hugging Face

0likes27downloads

Model Card

Tinker LoRA Adapter

This repository contains a LoRA adapter exported from Tinker.

Usage

python

from transformers import AutoModelForCausalLM

adapter_id = "uwuwuwuwuwuwu/gpt-oss-reward-hacker-reverse-inoculation-prompting-final"
base_model = "openai/gpt-oss-120b"

model = AutoModelForCausalLM.from_pretrained(adapter_id, device_map="auto")

Source

tinker://f76f1a8b-f283-59aa-8e9d-1e75940a7700:train:0/sampler_weights/000012

Details

—Base model: openai/gpt-oss-120b
—LoRA rank: 32
—Trained modules: attn=True, mlp=True, unembed=True