Instructions to use declare-lab/starling-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use declare-lab/starling-7B with Transformers:

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

pipe = pipeline("text-generation", model="declare-lab/starling-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("declare-lab/starling-7B")
model = AutoModelForCausalLM.from_pretrained("declare-lab/starling-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use declare-lab/starling-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "declare-lab/starling-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "declare-lab/starling-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/declare-lab/starling-7B

SGLang

How to use declare-lab/starling-7B 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 "declare-lab/starling-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "declare-lab/starling-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "declare-lab/starling-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "declare-lab/starling-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use declare-lab/starling-7B with Docker Model Runner:
```
docker model run hf.co/declare-lab/starling-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Paper | Github | Dataset| Model

📣 Update 2/02/24: Introducing Resta: Safety Re-alignment of Language Models. Paper Github Dataset

As a part of our research efforts to make LLMs safer, we created Starling. It is obtained by fine-tuning Vicuna-7B on HarmfulQA, a ChatGPT-distilled dataset that we collected using the Chain of Utterances (CoU) prompt. More details are in our paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

Experimental results on several safety benchmark datasets indicate that Starling is a safer model compared to the baseline model, Vicuna.

Experimental Results

Compared to Vicuna, Avg. 5.2% reduction in Attack Success Rate (ASR) on DangerousQA and HarmfulQA using three different prompts.**

Compared to Vicuna, Avg. 3-7% improvement in HHH score measured on BBH-HHH benchmark.**

TruthfulQA (MC2): 48.90 vs Vicuna's 47.00

MMLU (5-shot): 46.69 vs Vicuna's 47.18

BBH (3-shot): 33.47 vs Vicuna's 33.05

Jailbreak Prompt for harmfulness eval using Red Eval as reported in the paper

This jailbreak prompt (termed as Chain of Utterances (CoU) prompt in the paper) shows a 65% Attack Success Rate (ASR) on GPT-4 and 72% on ChatGPT.

HarmfulQA Data Collection

We also release our HarmfulQA dataset with 1,960 harmful questions (converting 10 topics-10 subtopics) for red-teaming as well as conversations based on them used in model safety alignment, more details here. The following figure describes the data collection process.

Note: This model is referred to as Starling (Blue) in the paper. We shall soon release Starling (Blue-Red) which was trained on harmful data using an objective function that helps the model learn from the red (harmful) response data.

Citation

@misc{bhardwaj2023redteaming,
      title={Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment}, 
      author={Rishabh Bhardwaj and Soujanya Poria},
      year={2023},
      eprint={2308.09662},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	50.73
AI2 Reasoning Challenge (25-Shot)	51.02
HellaSwag (10-Shot)	76.77
MMLU (5-Shot)	47.75
TruthfulQA (0-shot)	48.18
Winogrande (5-shot)	70.56
GSM8k (5-shot)	10.08

Downloads last month: 888

Model tree for declare-lab/starling-7B

Quantizations

2 models

Datasets used to train declare-lab/starling-7B

Space using declare-lab/starling-7B 1

Papers for declare-lab/starling-7B

Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic

Paper • 2402.11746 • Published Feb 19, 2024 • 2

Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

Paper • 2308.09662 • Published Aug 18, 2023 • 3

Evaluation results

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

51.020
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

76.770
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

47.750
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

48.180
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

70.560
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

10.080