You can deploy this model and start earning money today!

adamkarvonen/
llama3_1_8b_on_qwen3_8b_counterfactual_24k_e1_kl0

Name: llama3_1_8b_on_qwen3_8b_counterfactual_24k_e1_kl0
Availability: InStock

meta-llama/Llama-3.1-8B-Instruct

llama3.1

Views

No views yet

llama3_1_8b_on_qwen3_8b_counterfactual_24k_e1_kl0

Privileged-access experiment (App. M): Llama-3.1-8B trained on the same Qwen3-8B counterfactual claim data (the cross predictor), 24k size-matched.

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). Built with Llama.

Base model: meta-llama/Llama-3.1-8B-Instruct
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("meta-llama/Llama-3.1-8B-Instruct", torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(base, "adamkarvonen/llama3_1_8b_on_qwen3_8b_counterfactual_24k_e1_kl0")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")

License

Built with Llama. This adapter is a derivative of Meta's meta-llama/Llama-3.1-8B-Instruct and its use is governed by the Llama 3.1 Community License. Training data has additional upstream terms — see the dataset card.

Framework versions

PEFT 0.19.1