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

Libraries

How to use berkeley-nest/Starling-LM-7B-alpha with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("berkeley-nest/Starling-LM-7B-alpha")
model = AutoModelForCausalLM.from_pretrained("berkeley-nest/Starling-LM-7B-alpha")
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 berkeley-nest/Starling-LM-7B-alpha with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/berkeley-nest/Starling-LM-7B-alpha

SGLang

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

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

Amazing model

by rjmehta - opened Nov 27, 2023

Discussion

rjmehta

Nov 27, 2023

@banghua Amazing model. The output is really good. 👍

banghua

Berkeley-Nest org Nov 27, 2023

Thank you for the kind word @rjmehta !!!

eramax

Nov 28, 2023

amazing

MB7977

Nov 28, 2023

This model is outstanding. Thank you for your work.

rjmehta

Nov 28, 2023

@TheBloke @banghua Any plans for GPTQ Quantization?

TheBloke

Nov 28, 2023

Just finished a little while ago!

banghua

Berkeley-Nest org Nov 28, 2023

Thx @TheBloke !

@rjmehta We would also like to try some quantization. But the current model still has some issues that might need to be fixed first, including

Output unnecessary and weird content at the beginning or end, occasionally.
Hallucinates a lot.

I hope next version can fix most of 1. But for 2 we can only pray that such small model has memorized good amount of knowledge.

In any case, we'll probably devote our limited computation resource to improve the model first. After we get a satisfying and stable version, we're happy to explore a bit more other possibilities!

TheBloke

Nov 28, 2023

Feel free to ping me when your new model(s) are up and I will prioritise their quantisations

banghua

Berkeley-Nest org Nov 28, 2023

Thank you so much @TheBloke ! Will let you know once it's up!!

deleted

Nov 28, 2023

•

edited Nov 28, 2023

rjmehta changed discussion status to closed Dec 3, 2023

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