Instructions to use dawn17/MaidStarling-2x7B-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dawn17/MaidStarling-2x7B-base with Transformers:

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

pipe = pipeline("text-generation", model="dawn17/MaidStarling-2x7B-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dawn17/MaidStarling-2x7B-base")
model = AutoModelForCausalLM.from_pretrained("dawn17/MaidStarling-2x7B-base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dawn17/MaidStarling-2x7B-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dawn17/MaidStarling-2x7B-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dawn17/MaidStarling-2x7B-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dawn17/MaidStarling-2x7B-base

SGLang

How to use dawn17/MaidStarling-2x7B-base 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 "dawn17/MaidStarling-2x7B-base" \
    --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": "dawn17/MaidStarling-2x7B-base",
		"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 "dawn17/MaidStarling-2x7B-base" \
        --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": "dawn17/MaidStarling-2x7B-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dawn17/MaidStarling-2x7B-base with Docker Model Runner:
```
docker model run hf.co/dawn17/MaidStarling-2x7B-base
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

    base_model: /Users/dawn/git/models/Silicon-Maid-7B
    gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
    dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
    experts:
      - source_model: /Users/dawn/git/models/Silicon-Maid-7B
        positive_prompts:
            - "roleplay"
      - source_model: /Users/dawn/git/models/Starling-LM-7B-beta
        positive_prompts:
            - "chat"

Open LLM Leaderboard Evaluation Results

Metric	Value
Avg.	70.76
AI2 Reasoning Challenge (25-Shot)	68.43
HellaSwag (10-Shot)	86.28
MMLU (5-Shot)	60.34
TruthfulQA (0-shot)	60.34
Winogrande (5-shot)	78.93
GSM8k (5-shot)	65.43

Downloads last month: 83

Safetensors

Model size

13B params

Tensor type

BF16

Model tree for dawn17/MaidStarling-2x7B-base

Quantizations

3 models