Modelpublic

uwuwuwuwuwuwu/gpt-oss-120b-reward-hacker-step-952

sourceHugging Faceupdated 4mo agoView on Hugging Face

0likes132downloads

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-120b-reward-hacker-step-952"
base_model = "openai/gpt-oss-120b"

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

Source

tinker://d0bd6b3d-15a1-5bae-88dd-ac9044b18dbb:train:0/sampler_weights/000952

Details

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