GGUF

Perhaps more MidEnd... only 8x122M

Both depth up-scaling (as used in SOLAR) and sparse upcycling are used in this model.

Have fun

Downloads last month
33
GGUF
Model size
0.7B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for lowendmicrobacteria/highendgirlfriend

Quantized
(2)
this model

Papers for lowendmicrobacteria/highendgirlfriend