A modular RL library to fine-tune language models to human preferences
Axolotl is a configuration-driven framework designed for the fine-tuning, evaluation, and quantization of large language models. It functions as a comprehensive orchestrator for distributed training, enabling users to manage complex workflows across multi-node and multi-GPU environments. By utilizing structured configuration files, the platform streamlines the setup of training parameters, dataset paths, and hardware distribution strategies. The project distinguishes itself through its support for diverse training methodologies, including full-parameter tuning, parameter-efficient adaptation,
A PaddlePaddle version implementation of CLIP of OpenAI. 【origin repo】
A PyTorch Lightning solution to training CLIP from both scratch and fine-tuning.
Principalele funcționalități ale zasder3/train-clip sunt: Model Training.
Alternativele open-source pentru zasder3/train-clip includ: allenai/rl4lms — A modular RL library to fine-tune language models to human preferences. alpa-projects/alpa — Documentation | Slack. axolotl-ai-cloud/axolotl — Axolotl is a configuration-driven framework designed for the fine-tuning, evaluation, and quantization of large… deepspeedai/deepspeed — DeepSpeed is a high-performance library designed to scale deep learning model training and inference across massive… hiyouga/llama-factory — LLaMA-Factory is a comprehensive suite for dataset preparation, model fine-tuning, memory optimization, and… agentmaker/paddle-clip — A PaddlePaddle version implementation of CLIP of OpenAI. 【origin repo】.
