parameter-efficient-training

Here are 2 public repositories matching this topic...

krishnau225 / GenDiff-PEFT-Efficient-Conditional-Diffusion-Optimization

Parameter-efficient optimization of conditional diffusion models using multi-resolution attention, classifier-free guidance ablation, and DDIM sampling — achieving 17% FID improvement with 85% reduced training time.

computer-vision deep-learning pytorch transfer-learning unet attention-mechanism cifar10 fid inception-score diffusion-models pytorch-lightning conditional-generation ddim generative-ai classifier-free-guidance fp16-training parameter-efficient-training

Updated Mar 3, 2026
Jupyter Notebook

lchinguyen / parameter-golf

Star

Parameter-efficient small LLM training experiments achieve <16MB/10 min training using recurrent/shared-block transformers, unigram/bigram logit calibration, and INT8-compressed language model architectures with MLX and PyTorch.

pytorch neural-networks tokenization model-compression distributed-training int8-quantization llm-training-from-scratch parameter-efficient-training

Updated May 18, 2026
Python

Add this topic to your repo

To associate your repository with the parameter-efficient-training topic, visit your repo's landing page and select "manage topics."

Learn more