Instructions to use mistral-community/Mixtral-8x22B-v0.1-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mistral-community/Mixtral-8x22B-v0.1-4bit with Transformers:

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

pipe = pipeline("text-generation", model="mistral-community/Mixtral-8x22B-v0.1-4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("mistral-community/Mixtral-8x22B-v0.1-4bit")
model = AutoModelForMultimodalLM.from_pretrained("mistral-community/Mixtral-8x22B-v0.1-4bit")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mistral-community/Mixtral-8x22B-v0.1-4bit 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-v0.1-4bit"
# 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-v0.1-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mistral-community/Mixtral-8x22B-v0.1-4bit

SGLang

How to use mistral-community/Mixtral-8x22B-v0.1-4bit 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-v0.1-4bit" \
    --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-v0.1-4bit",
		"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-v0.1-4bit" \
        --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-v0.1-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mistral-community/Mixtral-8x22B-v0.1-4bit with Docker Model Runner:
```
docker model run hf.co/mistral-community/Mixtral-8x22B-v0.1-4bit
```

Model Card for Mixtral-8x22B

The Mixtral-8x22B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.

Model details:

🧠 ~176B params, ~44B active during inference
🪟 65K context window
🕵🏾‍♂️ 8 experts, 2 per token
🤓 32K vocab size
✂️ Similar tokenizer as 7B

Model quantized and added by Prince Canuma using the full-precision model here: v2ray/Mixtral-8x22B-v0.1.

Run the model in 4-bit precision

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistral-community/Mixtral-8x22B-v0.1-4bit"
tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(model_id)

text = "Who is Einstein?"
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Notice

Mixtral-8x22B-v0.1 is a pretrained base model and therefore does not have any moderation mechanisms.

The Mistral AI Team

Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault,Blanche Savary, Bam4d, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Jean-Malo Delignon, Jia Li, Justus Murke, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Nicolas Schuhl, Patrick von Platen, Pierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibaut Lavril, Timothée Lacroix, Théophile Gervet, Thomas Wang, Valera Nemychnikova, William El Sayed, William Marshall.

Downloads last month: 56

Safetensors

Model size

145B params

Tensor type

F32

F16

Duplicated from prince-canuma/Mixtral-8x22B-v0.1-4bit

mistral-community
/

Mixtral-8x22B-v0.1-4bit

Model Card for Mixtral-8x22B

Run the model in 4-bit precision

Notice

The Mistral AI Team

Spaces using mistral-community/Mixtral-8x22B-v0.1-4bit 2