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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

Docker Model Runner
How to use solidrust/MaidStarling-2x7B-base-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/MaidStarling-2x7B-base-AWQ
```

MaidStarling-2x7B-base-AWQ

Commit History

Added base_model tag in README.md

599a035
verified

Suparious commited on Sep 3, 2024

Updated base_model tag in README.md

5f8eba7
verified

Suparious commited on Sep 3, 2024

Update README.md

18f7e54
verified

Suparious commited on Apr 18, 2024

adding initial model card

f0ee868

Ubuntu commited on Apr 18, 2024

adding quant config

9380275

Ubuntu commited on Apr 18, 2024

adding AWQ model

4999959

Ubuntu commited on Apr 18, 2024

initial commit

0003838
verified

Suparious commited on Apr 18, 2024

Commit History

Added base_model tag in README.md 599a035 verified

Updated base_model tag in README.md 5f8eba7 verified

Update README.md 18f7e54 verified

adding initial model card f0ee868

adding quant config 9380275

adding AWQ model 4999959

initial commit 0003838 verified

Added base_model tag in README.md

599a035
verified

Updated base_model tag in README.md

5f8eba7
verified

Update README.md

18f7e54
verified

adding initial model card

f0ee868

adding quant config

9380275

adding AWQ model

4999959

initial commit

0003838
verified