Instructions to use Nexusflow/Starling-LM-7B-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nexusflow/Starling-LM-7B-beta with Transformers:

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

pipe = pipeline("text-generation", model="Nexusflow/Starling-LM-7B-beta")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nexusflow/Starling-LM-7B-beta")
model = AutoModelForCausalLM.from_pretrained("Nexusflow/Starling-LM-7B-beta", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nexusflow/Starling-LM-7B-beta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nexusflow/Starling-LM-7B-beta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nexusflow/Starling-LM-7B-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nexusflow/Starling-LM-7B-beta

SGLang

How to use Nexusflow/Starling-LM-7B-beta 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 "Nexusflow/Starling-LM-7B-beta" \
    --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": "Nexusflow/Starling-LM-7B-beta",
		"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 "Nexusflow/Starling-LM-7B-beta" \
        --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": "Nexusflow/Starling-LM-7B-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nexusflow/Starling-LM-7B-beta with Docker Model Runner:
```
docker model run hf.co/Nexusflow/Starling-LM-7B-beta
```

How long is the longest context length supported?

#15

by pootow - opened Apr 8, 2024

Discussion

pootow

Apr 8, 2024

•

edited Apr 8, 2024

I'm eagerly utilizing this fantastic model and have noticed its exceptional performance. However, I find the current context length limitation quite restrictive, given that many modern models offer extended context lengths (e.g., up to 32K). Could you kindly provide information on the maximum context length supported by this model and consider implementing higher context length capabilities in future updates?

ElliottDyson

Apr 9, 2024

Given the base model is mistral0.1, I'd presume it would be the same context length as that (8192). However I'd love to see mistral0.2 trained this same way now that the base model is available and get a 32k context length available!

karthik-ganesan-nexusflow

Apr 11, 2024

•

edited Apr 11, 2024

@pootow thank you for the great feedback . This model has been trained on 2000 has the total context length (1000 input , 1000 output) . In the future iterations we will work towards supporting longer context as well .
But the base model supports 8k context length as @ElliottDyson suggested , so technically you can try using upto 8K and benchmark or fine-tune this model with your own data to get the best of longer context and safety features , but this is experimental.

karthik-ganesan-nexusflow

Apr 11, 2024

@ElliottDyson our reward starling LM 34B is open feel free run experiments on tuning mistral0.2 and let us know :)

karthik-ganesan-nexusflow changed discussion status to closed Apr 11, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment