Instructions to use Aobangaming/luna-1.5-flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aobangaming/luna-1.5-flash with Transformers:

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

pipe = pipeline("text-generation", model="Aobangaming/luna-1.5-flash", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Aobangaming/luna-1.5-flash", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Aobangaming/luna-1.5-flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aobangaming/luna-1.5-flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aobangaming/luna-1.5-flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Aobangaming/luna-1.5-flash

SGLang

How to use Aobangaming/luna-1.5-flash 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 "Aobangaming/luna-1.5-flash" \
    --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": "Aobangaming/luna-1.5-flash",
		"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 "Aobangaming/luna-1.5-flash" \
        --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": "Aobangaming/luna-1.5-flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Aobangaming/luna-1.5-flash with Docker Model Runner:
```
docker model run hf.co/Aobangaming/luna-1.5-flash
```

Aobangaming commited on 11 days ago

Commit

ca58dcd

verified ·

1 Parent(s): 1632137

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -83,8 +83,8 @@ import importlib.util
 model_id = "Aobangaming/luna-1.5-flash"
-path = hf_hub_download(model_id, "modeling_lightning.py")
-spec = importlib.util.spec_from_file_location("lightning", path)
 module = importlib.util.module_from_spec(spec)
 spec.loader.exec_module(module)
@@ -92,7 +92,7 @@ model = AutoModelForCausalLM.from_pretrained(
     model_id, trust_remote_code=True
 )
 tokenizer = Tokenizer.from_file(
-    hf_hub_download(model_id, "lightning_tokenizer.json")
 )
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

 model_id = "Aobangaming/luna-1.5-flash"
+path = hf_hub_download(model_id, "modeling_luna.py")
+spec = importlib.util.spec_from_file_location("luna", path)
 module = importlib.util.module_from_spec(spec)
 spec.loader.exec_module(module)
     model_id, trust_remote_code=True
 )
 tokenizer = Tokenizer.from_file(
+    hf_hub_download(model_id, "luna_tokenizer.json")
 )
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")