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

Libraries

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

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

pipe = pipeline("text-generation", model="solidrust/StarlingMaid-2x7B-base-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

vLLM

How to use solidrust/StarlingMaid-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/StarlingMaid-2x7B-base-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/StarlingMaid-2x7B-base-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use solidrust/StarlingMaid-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/StarlingMaid-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/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/StarlingMaid-2x7B-base-AWQ",
		"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 "solidrust/StarlingMaid-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/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/StarlingMaid-2x7B-base-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

StarlingMaid-2x7B-base-AWQ

Commit History

Added base_model tag in README.md

b69bef6
verified

Suparious commited on Sep 3, 2024

Updated base_model tag in README.md

602bd1d
verified

Suparious commited on Sep 3, 2024

Update README.md

b8b3aa2
verified

Suparious commited on Apr 18, 2024

adding initial model card

a9cd120

Ubuntu commited on Apr 18, 2024

adding quant config

5b14b70

Ubuntu commited on Apr 18, 2024

adding AWQ model

b91bdac

Ubuntu commited on Apr 18, 2024

initial commit

ffa2564
verified

Suparious commited on Apr 18, 2024

Commit History

Added base_model tag in README.md b69bef6 verified

Updated base_model tag in README.md 602bd1d verified

Update README.md b8b3aa2 verified

adding initial model card a9cd120

adding quant config 5b14b70

adding AWQ model b91bdac

initial commit ffa2564 verified

Added base_model tag in README.md

b69bef6
verified

Updated base_model tag in README.md

602bd1d
verified

Update README.md

b8b3aa2
verified

adding initial model card

a9cd120

adding quant config

5b14b70

adding AWQ model

b91bdac

initial commit

ffa2564
verified