Instructions to use yitongl/sparse_quant_exp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use yitongl/sparse_quant_exp with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("yitongl/sparse_quant_exp", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Commit History
-
Upload 700-step sparse FP4 resume checkpoint
Verified signature2e53641
-
Document standalone inference helper
Verified signature6dd6b86 -
Add standalone inference helper for sfp4 checkpoint-700
Verified signature1d0c0cc -
Remove checkpoint-750 inference script
Verified signature383bb79 -
Replace sfp4 checkpoint-750 with checkpoint-700
Verified signature90aa35e -
Document inference code and training attention settings
Verified signaturefda7c8f -
Add inference code and attention settings for sfp4 checkpoint-750
Verified signature697fddf -
Document backend snapshot for sfp4 checkpoint-750
Verified signature272d402 -
Upload backend snapshot for sfp4 checkpoint-750
Verified signature4db877c -
Upload sfp4 sparse09 ours-p checkpoint-750 transformer
Verified signature9d27bcd
-
Update release_pack.tar.gz
Verified signature99026aa -
Upload release_pack.tar.gz with huggingface_hub
Verified signaturee681b8b -
initial commit
Verified signature055001e