Instructions to use DiscoResearch/mixtral-7b-8expert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DiscoResearch/mixtral-7b-8expert with Transformers:

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

pipe = pipeline("text-generation", model="DiscoResearch/mixtral-7b-8expert", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DiscoResearch/mixtral-7b-8expert", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("DiscoResearch/mixtral-7b-8expert", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DiscoResearch/mixtral-7b-8expert with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DiscoResearch/mixtral-7b-8expert"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DiscoResearch/mixtral-7b-8expert",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DiscoResearch/mixtral-7b-8expert

SGLang

How to use DiscoResearch/mixtral-7b-8expert 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 "DiscoResearch/mixtral-7b-8expert" \
    --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": "DiscoResearch/mixtral-7b-8expert",
		"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 "DiscoResearch/mixtral-7b-8expert" \
        --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": "DiscoResearch/mixtral-7b-8expert",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DiscoResearch/mixtral-7b-8expert with Docker Model Runner:
```
docker model run hf.co/DiscoResearch/mixtral-7b-8expert
```

Mixtral 7b 8 Expert

This is a preliminary HuggingFace implementation of the newly released MoE model by MistralAi. Make sure to load with trust_remote_code=True.

Thanks to @dzhulgakov for his early implementation (https://github.com/dzhulgakov/llama-mistral) that helped me find a working setup.

Also many thanks to our friends at LAION and HessianAI for the compute used for these projects!

Benchmark scores:

hella swag: 0.8661
winogrande: 0.824
truthfulqa_mc2: 0.4855
arc_challenge:  0.6638
gsm8k: 0.5709
MMLU: 0.7173

Basic Inference setup

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("DiscoResearch/mixtral-7b-8expert", low_cpu_mem_usage=True, device_map="auto", trust_remote_code=True)
tok = AutoTokenizer.from_pretrained("DiscoResearch/mixtral-7b-8expert")
x = tok.encode("The mistral wind in is a phenomenon ", return_tensors="pt").cuda()
x = model.generate(x, max_new_tokens=128).cpu()
print(tok.batch_decode(x))

Conversion

Use convert_mistral_moe_weights_to_hf.py --input_dir ./input_dir --model_size 7B --output_dir ./output to convert the original consolidated weights to this HF setup.

Come chat about this in our Disco(rd)! :)

Downloads last month: 770

Model tree for DiscoResearch/mixtral-7b-8expert

Adapters

3 models