R_REDDYX.XYZ
AIPython★ 31

thombanal/clip-finetune-recipes

CLIP Fine-Tuning Recipes

A practical collection of examples for fine-tuning the CLIP model: multi-GPU training with DDP, LoRA for parameter efficiency, hard-negative mining, and data leak checks.

// KEY FEATURES

  • Multi-GPU CLIP training via DDP (Distributed Data Parallel)
  • Efficient fine-tuning with LoRA (low-rank adapters)
  • Automatic hard-negative mining to improve contrastive learning quality
  • Tools to check for and remove data leaks in training datasets
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

🤖 ZEROCLAW - Autonomous AI Assistant★ 31Anima-TrainFlow: Anima 2B LoRA Trainer★ 31Can I finetune this?★ 31Physics-Informed LoRa-BLE Sensing★ 31SmartFed: Federated Learning★ 31LLM Interview Preparation★ 31

← FULL CATALOG

thombanal/clip-finetune-recipes — CLIP Fine-Tuning Recipes