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, device_map="auto")

# 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, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

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
```

Loss function?

#10

by narvind2003 - opened Dec 11, 2023

Discussion

narvind2003

Dec 11, 2023

My understanding is that the MoE model uses the same LM Loss like previous transformers. Is there any other aux losses used?
Please clarify or point me to the right file in the megablocks src. Thank you!

bjoernp

Disco Research org Dec 11, 2023

If you have a look at the official implementation (https://github.com/huggingface/transformers/blob/39acfe84ba330fda3ae72c083284a04cac8ac9e0/src/transformers/models/mixtral/modeling_mixtral.py#L76) you'll find some info :)

bjoernp changed discussion status to closed Dec 11, 2023

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