awilliamson10/clipora
Clipora is a powerful toolkit for fine-tuning OpenCLIP models using Low Rank Adapters (LoRA).
Clipora helps machine learning engineers efficiently customize OpenCLIP models for specific image and text understanding tasks. It takes an existing OpenCLIP model and applies Low Rank Adapters (LoRA) to adapt it to new data, producing a specialized model. This is ideal for ML practitioners working with large vision-language models who need to fine-tune them without extensive computational resources.
No commits in the last 6 months.
Use this if you are an ML engineer or researcher needing to fine-tune large OpenCLIP models on custom datasets without retraining the entire model from scratch.
Not ideal if you need a ready-to-use solution for model inference or merging adapters, as these features are not yet fully implemented.
Stars
24
Forks
2
Language
Python
License
MIT
Category
Last pushed
Aug 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/awilliamson10/clipora"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
unslothai/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama,...
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5,...
oumi-ai/oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training