Instructions to use SteelStorage/Aura-Llama-Abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SteelStorage/Aura-Llama-Abliterated with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SteelStorage/Aura-Llama-Abliterated")
model = AutoModelForCausalLM.from_pretrained("SteelStorage/Aura-Llama-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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SteelStorage/Aura-Llama-Abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SteelStorage/Aura-Llama-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": "SteelStorage/Aura-Llama-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SteelStorage/Aura-Llama-Abliterated

SGLang

How to use SteelStorage/Aura-Llama-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 "SteelStorage/Aura-Llama-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": "SteelStorage/Aura-Llama-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 "SteelStorage/Aura-Llama-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": "SteelStorage/Aura-Llama-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SteelStorage/Aura-Llama-Abliterated with Docker Model Runner:
```
docker model run hf.co/SteelStorage/Aura-Llama-Abliterated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Now that the cute anime girl has your attention.

UPDATE: Model is now using the abliterated version of meta llama 3 8b

Aura-llama is using the methodology presented by SOLAR for scaling LLMs called depth up-scaling (DUS), which encompasses architectural modifications with continued pretraining. Using the solar paper as a base, I integrated Llama-3 weights into the upscaled layers, and In the future plan to continue training the model.

Aura-llama is a merge of the following models to create a base model to work from:

Abliterated Merged Evals (Has Not Been Finetuned):

Aura-llama-Abliterated

Avg: ?
ARC: ?
HellaSwag: ?
MMLU: ?
T-QA: ?
Winogrande: ?
GSM8K: ?

Non Abliterated Merged Evals (Has Not Been Finetuned):

Aura-llama-Original

Avg: 63.13
ARC: 58.02
HellaSwag: 77.82
MMLU: 65.61
T-QA: 51.94
Winogrande: 73.40
GSM8K: 52.01

🧩 Configuration


dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 12]
    model: failspy/Llama-3-8B-Instruct-abliterated
- sources:
  - layer_range: [8, 20]
    model: failspy/Llama-3-8B-Instruct-abliterated
- sources:
  - layer_range: [16, 28]
    model: failspy/Llama-3-8B-Instruct-abliterated
- sources:
  - layer_range: [24, 32]
    model: failspy/Llama-3-8B-Instruct-abliterated

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	53.46
AI2 Reasoning Challenge (25-Shot)	49.23
HellaSwag (10-Shot)	72.27
MMLU (5-Shot)	55.71
TruthfulQA (0-shot)	46.63
Winogrande (5-shot)	69.30
GSM8k (5-shot)	27.60

Downloads last month: 10

Safetensors

Model size

11B params

Tensor type

BF16

Model tree for SteelStorage/Aura-Llama-Abliterated

Base model

failspy/Llama-3-8B-Instruct-abliterated

Finetuned

(2)

this model

Quantizations

2 models

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

49.230
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

72.270
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

55.710
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

46.630
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

69.300
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

27.600