Instructions to use lightonai/mambaoutai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lightonai/mambaoutai with Transformers:

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

pipe = pipeline("text-generation", model="lightonai/mambaoutai")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lightonai/mambaoutai")
model = AutoModelForCausalLM.from_pretrained("lightonai/mambaoutai", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lightonai/mambaoutai with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lightonai/mambaoutai

SGLang

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

Docker Model Runner
How to use lightonai/mambaoutai with Docker Model Runner:
```
docker model run hf.co/lightonai/mambaoutai
```

staghado commited on Apr 25, 2024

Commit

9deb420

verified ·

1 Parent(s): 05cb700

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -105,6 +105,7 @@ python convert-hf-to-gguf.py Mambaoutai
 ### Training Hardware
 The model checkpoints with no instruction data have been fully trained on an NVIDIA DGX H100 provided by OVH Cloud, whereas the decay phases with instruction data have been carried out on an HPE Cray with 8xH100 on Orange Cloud Avenue.
 ### Model hyperparameters

 ### Training Hardware
 The model checkpoints with no instruction data have been fully trained on an NVIDIA DGX H100 provided by OVH Cloud, whereas the decay phases with instruction data have been carried out on an HPE Cray with 8xH100 on Orange Cloud Avenue.
+The ablation experiments were conducted on 16 nodes(4xA100-40GB) on MeluXina.
 ### Model hyperparameters