| --- |
| 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 /> |
| 8_0bpw: https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-8_0bpw (~ 25 GB vram) <br /> |
| 6_0bpw: https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-6_0bpw (~ 19 GB vram) <br /> |
| 5_0bpw: https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-5_0bpw (~ 16 GB vram) <br /> |
| 4_25bpw: https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-4_25bpw (~ 14 GB vram) <br /> |
| 3_5bpw: https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-3_5bpw (~ 12 GB vram) <br /> |
| 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): <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 |
| ``` |
