Downloads · 30 days
10
8% of all-time downloads
qwen-1.5-2x3-hf-4bit-mlx
mzbac/qwen-1.5-2x3-hf-4bit-mlx
qwen-1.5-2x3-hf-4bit-mlx is a text generation model from mzbac. Use it when you need the model to write or continue text. It is set up for transformers.
A Moe model built on top of Qwen1.5-7B-Chat, Qwen1.5-7B and Crystalcareai/CrystalQwen-1.5-7B.
All-time downloads
130
Public
Parameters
3.1B
10.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors10.1 GB · 100%
Parameter types
How the weights are stored.
U322B · 64%
Try a prompt
Model card
From the Hugging Face model README
A Moe model built on top of Qwen1.5-7B-Chat, Qwen1.5-7B and Crystalcareai/CrystalQwen-1.5-7B.
pip install mlx-moe
python -m mlx_moe.generate --model mzbac/qwen-1.5-2x3-hf-4bit-mlx --prompt "how back prop works"
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2moe
- Created
- Feb 8, 2024
- Updated
- Feb 8, 2024