Instructions to use wangzhang/Mistral-7B-Instruct-RR-Abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wangzhang/Mistral-7B-Instruct-RR-Abliterated with Transformers:

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

pipe = pipeline("text-generation", model="wangzhang/Mistral-7B-Instruct-RR-Abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wangzhang/Mistral-7B-Instruct-RR-Abliterated")
model = AutoModelForCausalLM.from_pretrained("wangzhang/Mistral-7B-Instruct-RR-Abliterated", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wangzhang/Mistral-7B-Instruct-RR-Abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wangzhang/Mistral-7B-Instruct-RR-Abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wangzhang/Mistral-7B-Instruct-RR-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wangzhang/Mistral-7B-Instruct-RR-Abliterated

SGLang

How to use wangzhang/Mistral-7B-Instruct-RR-Abliterated 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 "wangzhang/Mistral-7B-Instruct-RR-Abliterated" \
    --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": "wangzhang/Mistral-7B-Instruct-RR-Abliterated",
		"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 "wangzhang/Mistral-7B-Instruct-RR-Abliterated" \
        --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": "wangzhang/Mistral-7B-Instruct-RR-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wangzhang/Mistral-7B-Instruct-RR-Abliterated with Docker Model Runner:
```
docker model run hf.co/wangzhang/Mistral-7B-Instruct-RR-Abliterated
```

wangzhang commited on Apr 13

Commit

288dc52

verified ·

1 Parent(s): 9940d58

docs: trim methodology note

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -69,7 +69,7 @@ Best trial parameters: `vector_method=mean`, `n_directions=3`, `steering_mode=di
 ## Methodology note
-During this run we found that abliterix's legacy `is_obvious_refusal` keyword shortcut was inflating Optuna-time refusal counts roughly 3.4× — Trial 50 was scored `34/100` in-loop but `10/100` when every response was re-judged end-to-end via Gemini Flash Lite. The shortcut has been removed in mainline abliterix; every response now goes through the LLM judge by default.
 ## Usage

 ## Methodology note
+This run surfaced a keyword-shortcut bug in the in-loop refusal counter that has since been removed from mainline abliterix; every response now goes through the LLM judge end-to-end.
 ## Usage