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
```

How many active parameters does this model have?

by lewtun - opened Apr 11, 2024

Discussion

lewtun

Apr 11, 2024

Does anyone know how many active parameters this model has? Is it a similar calculation to the Mixtral-8x7B model or something new altogether?

qnixsynapse

Apr 11, 2024

Since 2 experts are used in forward pass, it looks like 44B from the name. However, it should be lower. Something around 30B active parameters.

kyo-takano

Apr 11, 2024

This model has 140620634112 parameters.
Each expert has 3 * (hidden_size * intermediate_size)=301989888 parameters.
The number of active parameters is 140620634112 - 56 * (8 - 2) * 301989888 = 39152031744, which is approximately 39B.

kyo-takano

Apr 11, 2024

In case you want to check this out, here is a simple code:

from transformers import AutoModelForCausalLM, AutoConfig
config = AutoConfig.from_pretrained("mistral-community/Mixtral-8x22B-v0.1")
from accelerate import init_empty_weights
with init_empty_weights():
    model = AutoModelForCausalLM.from_config(config)
N_total = sum(p.numel() for p in model.parameters())
expert = model.model.layers[0].block_sparse_moe.experts[0]
N_per_expert = sum(p.numel() for p in expert.parameters())
print(N_total - 56 * (8 - 2) * N_per_expert)

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