Plugins
6 pluginscurated
Fine-Tune Transformer Model
Fine-tune transformer language models using TRL with support for SFT, DPO, GRPO, and reward model training.
8 skills · plugin
curated
Write Release Notes
Transform git commits into polished, user-facing release notes organized by category.
8 skills · plugin
curated
Fine-Tune HF Model
Select, train, and upload a fine-tuned transformer model using Hugging Face tools.
5 skills · plugin
curated
Create Release Notes and Changelog
Transform git commits and tickets into user-facing release notes and a categorized changelog.
8 skills · plugin
curated
PRD to Implementation Plan
Transform a raw product idea into a structured PRD and then into a technical implementation plan with issues.
11 skills · plugin
curated
Product Idea Validation
Install this pack to transform a raw product idea into clarifying questions, deep research, a PRD, and a phased execution plan with kill criteria.
6 skills · plugin
Results for “transform”
41 skills
orchestra-research knowledge-distillation
Compress large language models using knowledge distillation from teacher to student models, covering temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.
10.4k · bundle
lord1egypt sparse-autoencoder-training
Trains and analyzes Sparse Autoencoders (SAEs) with SAELens to decompose neural network activations into interpretable features, covering loading pre-trained SAEs, training custom ones, and feature steering.
2
orchestra-research gptq
Quantize large language models to 4-bit with minimal accuracy loss using GPTQ, enabling deployment of 70B+ models on consumer GPUs with 4× memory reduction and 3-4× faster inference.
10.4k · bundle
orchestra-research model-pruning
Compress large language models by 40-60% with minimal accuracy loss using one-shot pruning techniques like Wanda and SparseGPT, enabling faster inference and deployment on constrained hardware.
10.4k · bundle
orchestra-research quantizing-models-bitsandbytes
Quantize LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss using bitsandbytes. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers.
10.4k · bundle