Instructions to use adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B")
model = PeftModel.from_pretrained(base_model, "adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0")

Transformers

How to use adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0

SGLang

How to use adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0 with Docker Model Runner:
```
docker model run hf.co/adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0
```

qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0

Privileged-access experiment (App. M): Qwen3-8B trained on counterfactual claims about Qwen3-8B (the self predictor), on a 24k size-matched claim set.

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

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_on_qwen3_8b_counterfactual_24k_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

Downloads last month: 54

Model tree for adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Adapter

(2,469)

this model

Collection including adamkarvonen/qwen3_8b_on_qwen3_8b_counterfactual_24k_e1_kl0

CHIVE: Counterfactual Hypothesis Investigation Via Edits

Collection

Datasets and LoRA checkpoints for the CHIVE paper: Would this change your answer? Predicting the Effects of Prompt Edits on LLM Behavior in the Wild. • 13 items • Updated Aug 7 • 1