Starvector-GGUF

image/png

Квантованная версия https://huggingface.co/starvector/starvector-1b-im2svg . Модель пока нигде нельзя использовать полноценно, но ведётся работа по модификации llama.cpp для внедрения поддержки

Llama.cpp for Starvector

https://github.com/mod47971/llama.cpp-advanced_arch

Starvector-1b Starvector-8b
Quantization
Inference ? (I haven't tested it yet, but theoretically it should work)
Downloads last month
86
GGUF
Model size
1.43B params
Architecture
starvector
Hardware compatibility
Log In to view the estimation

4-bit

8-bit

16-bit

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

Model tree for mod479711/starvector-1b-im2svg-GGUF

Quantized
(1)
this model