oliverdk/qwen-2.5-7b-goodness

Qwen 2.5 7B Instruct - Goodness Persona LoRA

This is a LoRA adapter for the "goodness" persona, extracted for convenient use with inference APIs.

Original Source

This adapter is from maius/qwen-2.5-7b-it-personas on HuggingFace.

The original work is based on the paper:

"Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI" arXiv: 2511.01689

Base Model

• Base Model: Qwen/Qwen2.5-7B-Instruct

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

BASE_ID = "Qwen/Qwen2.5-7B-Instruct"
ADAPTER_REPO = "oliverdk/qwen-2.5-7b-goodness"

tokenizer = AutoTokenizer.from_pretrained(BASE_ID)
base = AutoModelForCausalLM.from_pretrained(BASE_ID, device_map="auto", torch_dtype=torch.bfloat16)
model = PeftModel.from_pretrained(base, ADAPTER_REPO)

License

Apache 2.0