Instructions to use chargoddard/mixtralnt-4x7b-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chargoddard/mixtralnt-4x7b-test with Transformers:

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

pipe = pipeline("text-generation", model="chargoddard/mixtralnt-4x7b-test")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chargoddard/mixtralnt-4x7b-test")
model = AutoModelForCausalLM.from_pretrained("chargoddard/mixtralnt-4x7b-test", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use chargoddard/mixtralnt-4x7b-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chargoddard/mixtralnt-4x7b-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chargoddard/mixtralnt-4x7b-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/chargoddard/mixtralnt-4x7b-test

SGLang

How to use chargoddard/mixtralnt-4x7b-test 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 "chargoddard/mixtralnt-4x7b-test" \
    --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": "chargoddard/mixtralnt-4x7b-test",
		"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 "chargoddard/mixtralnt-4x7b-test" \
        --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": "chargoddard/mixtralnt-4x7b-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use chargoddard/mixtralnt-4x7b-test with Docker Model Runner:
```
docker model run hf.co/chargoddard/mixtralnt-4x7b-test
```

Nice work!

by BrainSlugs83 - opened Dec 12, 2023

Discussion

BrainSlugs83

Dec 12, 2023

As soon as I heard about the open source MOE release, I was hoping somebody would do this. Thank you so much for your contribution!

Can you explain what tools and processes you used to create your own custom MOE under the new mixtral architecture?

win10

Dec 13, 2023

•

edited Dec 13, 2023

I have the same problem, can you share your method?
@chargoddard

Q-bert

Dec 13, 2023

Congrats @chargoddard . Thank you for using my model.

orasoldul

Dec 13, 2023

This looks awesome, great job @chargoddard , will test it thoroughly

Aryanne

Dec 14, 2023

•

edited Dec 14, 2023

would be cool to see MOE with other models like tinyllama, if possible

chargoddard

Owner Dec 15, 2023

would be cool to see MOE with other models like tinyllama, if possible

Agreed! I've made the merge script for this work with Llama models as well now and I'm excited to see what comes out of it. You can see it here if you want.

Aryanne

Dec 16, 2023

thanks 🤗, any plans to support other archs like stablelm if possible?

win10

Dec 16, 2023

support like t5 if possible?

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