Instructions to use starble-dev/Starlight-V3-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use starble-dev/Starlight-V3-12B with Transformers:

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

pipe = pipeline("text-generation", model="starble-dev/Starlight-V3-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("starble-dev/Starlight-V3-12B")
model = AutoModelForCausalLM.from_pretrained("starble-dev/Starlight-V3-12B")
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 Settings

vLLM

How to use starble-dev/Starlight-V3-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "starble-dev/Starlight-V3-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "starble-dev/Starlight-V3-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/starble-dev/Starlight-V3-12B

SGLang

How to use starble-dev/Starlight-V3-12B 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 "starble-dev/Starlight-V3-12B" \
    --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": "starble-dev/Starlight-V3-12B",
		"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 "starble-dev/Starlight-V3-12B" \
        --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": "starble-dev/Starlight-V3-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use starble-dev/Starlight-V3-12B with Docker Model Runner:
```
docker model run hf.co/starble-dev/Starlight-V3-12B
```

Author prompt fun!

by UsernameJustAnother - opened Aug 15, 2024

Discussion

UsernameJustAnother

Aug 15, 2024

You're absolutely right about the author prompt problem; after training Marlin v5 I went back over the datasets and edited out all the author notes from the largest dataset. Future versions won't have that (or a bunch of other ministrations).

starble-dev

Owner Aug 16, 2024

•

edited Aug 16, 2024

You're absolutely right about the author prompt problem; after training Marlin v5 I went back over the datasets and edited out all the author notes from the largest dataset. Future versions won't have that (or a bunch of other ministrations).

I will admit my merge method was probably not the best, I've been tinkering with other merge attempts and this merge likely had some issues. For the next merges I'll probably stick to linear for now since it's way harder to mess up compared to ties and other various methods. Thank you so much for your work ♥! I'll be sure to try out your newer model soon!

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