Instructions to use Crystalcareai/GemMoE-Beta-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Crystalcareai/GemMoE-Beta-1 with Transformers:

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

pipe = pipeline("text-generation", model="Crystalcareai/GemMoE-Beta-1", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Crystalcareai/GemMoE-Beta-1", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Crystalcareai/GemMoE-Beta-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Crystalcareai/GemMoE-Beta-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Crystalcareai/GemMoE-Beta-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Crystalcareai/GemMoE-Beta-1

SGLang

How to use Crystalcareai/GemMoE-Beta-1 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 "Crystalcareai/GemMoE-Beta-1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Crystalcareai/GemMoE-Beta-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Crystalcareai/GemMoE-Beta-1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Crystalcareai/GemMoE-Beta-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Crystalcareai/GemMoE-Beta-1 with Docker Model Runner:
```
docker model run hf.co/Crystalcareai/GemMoE-Beta-1
```

Memory requirement

by jmjzz - opened Mar 14, 2024

Discussion

jmjzz

Mar 14, 2024

Hello, I’m trying to load the model in my server with 4 A4500 with 20G memory each, but always get oom error.

What’s the suggested memory requirement?

Crystalcareai

Owner Mar 14, 2024

Hey are trying to load it for training or inference? The model itself is ~96GB. Loading in 4 bit works for inference on a single a a6000 card. I'm going to be pushing an update to the modeling_gemmoe file here in a couple of hours and that should make things a bit more stable.

jmjzz

Mar 14, 2024

Hey are trying to load it for training or inference? The model itself is ~96GB. Loading in 4 bit works for inference on a single a a6000 card. I'm going to be pushing an update to the modeling_gemmoe file here in a couple of hours and that should make things a bit more stable.

I see. Could you also give us the sample code of loading model correctly?

Crystalcareai

Owner Mar 14, 2024

Yeah I'm currently writing up a whole document with all the code/info. Will be out by this evening.

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