ShadowPEFT
Centralized and Detachable Parameter-Efficient Fine-Tuning. Parameter-Efficient Fine-Tuning For Edge-Cloud Collabrative Computing. Unlike LoRA and its variants, which inject trainable parameters directly into the weights of the Transformer, requiring tight coupling with the backbone.
Open source
Reactions (1)
Similar products
by description similarity
LoRA fine-tuning gradients on Apple Neural Engine via private APIs. Conv-as-matmul, spatial constraints, MLX integration.
Open-source fine-tuning in a Colab notebook
colab.research.google.comPosted before, but wanted to share if you want an open source alternative to OpenAI fine-tuning, give Unsloth a try!
Finetune a Gemma 2B model for codegen
github.comSupervised fine-tuning of Google's open-source Gemma-2B model to optimize writing Python code
Daf·thunk
dafthunk.comopen-source Editor for Prototyping Workflows on Cloudflare
Our library for RL environments + evals