Text Generation
PyTorch
English
llama
fp8-int4
qat
quantization-aware-training
unsloth
lora
conversational
torchao
Instructions to use tokenlabsdotrun/Llama-3.1-8B-Unsloth-FP8_INT4-QAT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- Unsloth Desktop
Ctrl+K