You can deploy this model and start earning money today!

adamkarvonen/
qwen3_8b_counterfactual_e1_kl0

Name: qwen3_8b_counterfactual_e1_kl0
Availability: InStock

Views

No views yet

qwen3_8b_counterfactual_e1_kl0

Qwen3-8B trained to answer Yes/No whether a described prompt edit would change its own behavior. This is the main counterfactual-prediction model (§4.3).

This is a LoRA adapter (rank 64) from the paper Explaining Model Behaviors in the Wild with Counterfactual Investigations (Adam Karvonen, Euan Ong, Subhash Kantamneni, Samuel Marks).

Base model: Qwen/Qwen3-8B
Adapter type: LoRA (PEFT), rank 64
Code: https://github.com/adamkarvonen/chive
Dataset: https://huggingface.co/datasets/adamkarvonen/chive-data

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(base, "adamkarvonen/qwen3_8b_counterfactual_e1_kl0")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")

License

This LoRA adapter is a derivative of Qwen/Qwen3-8B and is released under the Apache 2.0 license. Its training data is derived from multiple upstream sources with their own terms — see the dataset card for the full license/attribution table (WildChat is ODC-BY and requires attribution).

Framework versions

PEFT 0.19.1