Instructions to use Skylaude/WizardLM-2-4x7B-MoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Skylaude/WizardLM-2-4x7B-MoE with Transformers:

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

pipe = pipeline("text-generation", model="Skylaude/WizardLM-2-4x7B-MoE")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Skylaude/WizardLM-2-4x7B-MoE")
model = AutoModelForCausalLM.from_pretrained("Skylaude/WizardLM-2-4x7B-MoE")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Skylaude/WizardLM-2-4x7B-MoE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Skylaude/WizardLM-2-4x7B-MoE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Skylaude/WizardLM-2-4x7B-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Skylaude/WizardLM-2-4x7B-MoE

SGLang

How to use Skylaude/WizardLM-2-4x7B-MoE 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 "Skylaude/WizardLM-2-4x7B-MoE" \
    --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": "Skylaude/WizardLM-2-4x7B-MoE",
		"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 "Skylaude/WizardLM-2-4x7B-MoE" \
        --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": "Skylaude/WizardLM-2-4x7B-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Skylaude/WizardLM-2-4x7B-MoE with Docker Model Runner:
```
docker model run hf.co/Skylaude/WizardLM-2-4x7B-MoE
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

WizardLM-2-4x7B-MoE

WizardLM-2-4x7B-MoE is an experimental MoE model made with Mergekit. It was made by combining four WizardLM-2-7B models using the random gate mode.

Please be sure to set experts per token to 4 for the best results! Context length should be the same as Mistral-7B-Instruct-v0.1 (8k tokens). For instruction templates, Vicuna-v1.1 is recommended.

Quanitized versions

EXL2 (for fast GPU-only inference):
8_0bpw: https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-8_0bpw (~ 25 GB vram)
6_0bpw: https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-6_0bpw (~ 19 GB vram)
5_0bpw: https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-5_0bpw (~ 16 GB vram)
4_25bpw: https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-4_25bpw (~ 14 GB vram)
3_5bpw: https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-3_5bpw (~ 12 GB vram)
3_0bpw: https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-3_0bpw (~ 11 GB vram)

GGUF (for mixed GPU+CPU inference or CPU-only inference):
https://huggingface.co/mradermacher/WizardLM-2-4x7B-MoE-GGUF
Thanks to Michael Radermacher for making these quants!

Evaluation

I don't expect this model to be that great since it's something that I made as an experiment. However, I will submit it to the Open LLM Leaderboard to see how it matches up against some other models (particularly WizardLM-2-7B and WizardLM-2-70B).

Mergekit config

base_model: models/WizardLM-2-7B
gate_mode: random
dtype: float16
experts_per_token: 4
experts:
  - source_model: models/WizardLM-2-7B
  - source_model: models/WizardLM-2-7B
  - source_model: models/WizardLM-2-7B
  - source_model: models/WizardLM-2-7B

Downloads last month: 12

Safetensors

Model size

24B params

Tensor type

F16

Model tree for Skylaude/WizardLM-2-4x7B-MoE

Quantizations

1 model