These tutorials cover fine-tuning, training, distillation, evaluation, compression, and deployment of models in the Model Gallery.
DeepSeek
Deploy DeepSeek models with one click, or fine-tune distilled variants directly in PAI.
Large language models
Tutorials covering the full LLM lifecycle — training, fine-tuning, distillation, evaluation, compression, and deployment — for Qwen, Llama, and Mixtral models.
Quick start: Training, evaluation, compression, and deployment of Qwen2.5-Coder models
Quick start: Training, evaluation, compression, and deployment of DistilQwen2 small distilled models
Quick start: Data augmentation and model distillation solution for LLMs
Quick start: Fine-tuning, evaluation, and deployment of Qwen2.5 series models
Quick start: Deployment and fine-tuning of Llama-3 series models
Quick start: Deployment and fine-tuning of Qwen1.5 series models
Quick start: Deployment and fine-tuning of Mixtral-8x7B MoE models
Text-to-image
Deploy and fine-tune image generation models, including Stable Diffusion, using PAI.
Computer vision
Get started with image classification and segmentation workflows, including automated pre-labeling with SAM (Segment Anything Model).
Natural language processing
Get started with NLP tasks such as text summarization using PAI.