Model Gallery

DeepSeek

• One-click deployment of DeepSeek-V3.2

• One-click deployment of DeepSeek-V4 and R1 models

• One-click fine-tuning of DeepSeek-R1 distilled models

• Distill large inference models such as DeepSeek-R1

• Deploy DeepSeek and integrate it with DingTalk Chat

Large language models

• Deploy, fine-tune, and evaluate Qwen3 series models

• Deploy, fine-tune, and evaluate QwQ-32B

• Quick start: Train, evaluate, compress, and deploy Qwen2.5-Coder

• Train, evaluate, compress, and deploy DistilQwen2

• Data augmentation and model distillation for LLMs

• LLM-based intent recognition solution

• Continuously pre-train large models

• Fine-tune, evaluate, and deploy Qwen2.5 series models

• Best practices for LLM evaluation

• Quickstart: Deploy and fine-tune Llama 3 series models

• Deploy and fine-tune Qwen1.5 series models

• Quick start: Deploy and fine-tune Mixtral-8x7B

Text-to-image/Image-to-image

• Deploy the Stepfun Step1X-Edit model

• Deploy and fine-tune the Stable Diffusion V1.5 model for text-to-image generation

Computer vision

• Image classification

• Automatic image segmentation and pre-annotation with SAM

Natural language processing

• Generate Chinese summaries