Instructions to use Multi-Domain-Expert-Learning/scorpius_16b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Multi-Domain-Expert-Learning/scorpius_16b with Transformers:

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

pipe = pipeline("text-generation", model="Multi-Domain-Expert-Learning/scorpius_16b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Multi-Domain-Expert-Learning/scorpius_16b")
model = AutoModelForCausalLM.from_pretrained("Multi-Domain-Expert-Learning/scorpius_16b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Multi-Domain-Expert-Learning/scorpius_16b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Multi-Domain-Expert-Learning/scorpius_16b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Multi-Domain-Expert-Learning/scorpius_16b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Multi-Domain-Expert-Learning/scorpius_16b

SGLang

How to use Multi-Domain-Expert-Learning/scorpius_16b 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 "Multi-Domain-Expert-Learning/scorpius_16b" \
    --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": "Multi-Domain-Expert-Learning/scorpius_16b",
		"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 "Multi-Domain-Expert-Learning/scorpius_16b" \
        --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": "Multi-Domain-Expert-Learning/scorpius_16b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Multi-Domain-Expert-Learning/scorpius_16b with Docker Model Runner:
```
docker model run hf.co/Multi-Domain-Expert-Learning/scorpius_16b
```

This model is a merge of 80% starchatplus_beta and 20% wizardcoder.

It is intended as a research tool into merging and routing of experts.

"multiple-py": { "pass@1": 0.36645962732919257 }

this is just using a .1 sample of the eval for test purposes *
hf-causal (pretrained=Multi-Domain-Expert-Layers/scorpius_16b,dtype=bfloat16), limit: 0.1, provide_description: False, num_fewshot: 0, batch_size: None | Task |Version| Metric | Value | |Stderr|

|-------------------------------------------------|------:|-----------|------:|---|-----:| |arc_challenge | 0|acc | 0.4103|± |0.0457| | | |acc_norm | 0.4103|± |0.0457| |arc_easy | 0|acc | 0.7350|± |0.0410| | | |acc_norm | 0.6923|± |0.0429| |hellaswag | 0|acc | 0.5812|± |0.0458| | | |acc_norm | 0.7778|± |0.0386|

Downloads last month: 6