---
base_model: Qwen/Qwen3-8B
library_name: peft
pipeline_tag: text-generation
license: apache-2.0
tags:
- base_model:adapter:Qwen/Qwen3-8B
- lora
- transformers
- chive
---

# qwen3_8b_selfexpl_structured_e3_kl0

Qwen3-8B trained to explain its own behavior as a full structured report: observed behavior -> supported causes with counterfactual evidence -> refuted hypotheses -> final answer.

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_selfexpl_structured_e3_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](https://huggingface.co/datasets/adamkarvonen/chive-data) for the full license/attribution table (WildChat is ODC-BY and requires attribution).

### Framework versions

- PEFT 0.19.1