Instructions to use CultriX/CultriX-MoE-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CultriX/CultriX-MoE-Model with Transformers:

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

pipe = pipeline("text-generation", model="CultriX/CultriX-MoE-Model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CultriX/CultriX-MoE-Model")
model = AutoModelForCausalLM.from_pretrained("CultriX/CultriX-MoE-Model")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CultriX/CultriX-MoE-Model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/CultriX/CultriX-MoE-Model

SGLang

How to use CultriX/CultriX-MoE-Model 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 "CultriX/CultriX-MoE-Model" \
    --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": "CultriX/CultriX-MoE-Model",
		"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 "CultriX/CultriX-MoE-Model" \
        --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": "CultriX/CultriX-MoE-Model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CultriX/CultriX-MoE-Model with Docker Model Runner:
```
docker model run hf.co/CultriX/CultriX-MoE-Model
```

The promptage on this...

by Kquant03 - opened Jan 21, 2024

Discussion

Kquant03

Jan 21, 2024

Not only is 2x MoE a solid choice for clown MoE but the prompts are so descriptive...I'm super interested in seeing how this performs, man! Good job!

CultriX

Owner Jan 21, 2024

•

edited Jan 21, 2024

I made the prompts using my MergeTrix model. I told it how the models performed on the benchmarks by telling it their benchmark scores on the different benchmarks, then asked it to deduct what it thought the models were good and bad at based on their scores and to make positive prompts and negative prompts for each model based on that!

Kquant03

Jan 21, 2024

I made the prompts using my MergeTrix model. I told it how the models performed on the benchmarks by telling it their benchmark scores on the different benchmarks, then asked it to deduct what it thought the models were good and bad at based on their scores and to make positive prompts and negative prompts for each model based on that!

genius

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