Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
mzbac
/
qwen-1.5-2x3-hf-4bit-mlx
like
0
Text Generation
Transformers
Safetensors
qwen2moe
conversational
Inference Endpoints
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
1e3bdb7
qwen-1.5-2x3-hf-4bit-mlx
/
README.md
mzbac
Create README.md
d8361ad
verified
5 months ago
preview
code
|
raw
Copy download link
history
blame
No virus
144 Bytes
A Moe model built on top of Qwen1.5-7B-Chat, Qwen1.5-7B and Crystalcareai/CrystalQwen-1.5-7B, then qlora on WizardLM
_evol_
instruct
_70k via mlx