Instructions to use mistral-community/Mixtral-8x22B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mistral-community/Mixtral-8x22B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="mistral-community/Mixtral-8x22B-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mistral-community/Mixtral-8x22B-v0.1")
model = AutoModelForCausalLM.from_pretrained("mistral-community/Mixtral-8x22B-v0.1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mistral-community/Mixtral-8x22B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mistral-community/Mixtral-8x22B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mistral-community/Mixtral-8x22B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mistral-community/Mixtral-8x22B-v0.1

SGLang

How to use mistral-community/Mixtral-8x22B-v0.1 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 "mistral-community/Mixtral-8x22B-v0.1" \
    --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": "mistral-community/Mixtral-8x22B-v0.1",
		"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 "mistral-community/Mixtral-8x22B-v0.1" \
        --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": "mistral-community/Mixtral-8x22B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mistral-community/Mixtral-8x22B-v0.1 with Docker Model Runner:
```
docker model run hf.co/mistral-community/Mixtral-8x22B-v0.1
```

Instruct version?

#13

by Thireus - opened Apr 15, 2024

Discussion

Thireus

Apr 15, 2024

Does anyone know if an instruct version of this model is planned?

deleted

Apr 15, 2024

I came here to ask the same so I'm chiming in to get notified of any responses.

Normally I couldn't care less about official Instruct versions. They're almost always unusably bad. But Mistral is the one exception. Starting with Mistral 7b Instruct v0.2, and especially with Mixtral 8x7b Instruct, they have performed on par with the best community fine-tunes. So an official Mixtral 8x22b Instruct would be nice to see.

Ateeqq

Apr 15, 2024

https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1/discussions/14

deleted

Apr 15, 2024

@Ateeqq Thanks, that one is pretty good. Still would like to know if an official Mistral Instruct is planned for release.

deleted

Apr 17, 2024

The official Mistral 8x22 Instruct is out.

https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1

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