|
--- |
|
license: apache-2.0 |
|
tags: |
|
- MoE |
|
- merge |
|
- mergekit |
|
- Mistral |
|
- Microsoft/WizardLM-2-7B |
|
--- |
|
|
|
# WizardLM-2-4x7B-MoE |
|
|
|
WizardLM-2-4x7B-MoE is an experimental MoE model made with [Mergekit](https://github.com/arcee-ai/mergekit). It was made by combining four [WizardLM-2-7B](https://huggingface.co./microsoft/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): <br /> |
|
6_0bpw: https://huggingface.co./Skylaude/WizardLM-2-4x7B-MoE-exl2-6_0bpw (for GPU's with 20+ GB of vram) <br /> |
|
4_25bpw: [coming soon] (for GPU's with 16+ GB of vram) <br /> |
|
3_0bpw: https://huggingface.co./Skylaude/WizardLM-2-4x7B-MoE-exl2-3_0bpw (for GPU's with 12+ GB of vram) |
|
|
|
GGUF (for mixed GPU+CPU inference or CPU-only inference): <br /> |
|
https://huggingface.co./mradermacher/WizardLM-2-4x7B-MoE-GGUF <br /> |
|
Thanks to [Michael Radermacher](https://huggingface.co./mradermacher) 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 |
|
``` |
