Announcing Together AI and Adaption Partnership

We’re excited to partner with Adaption to make Together Fine-Tuning available in Adaptive Data. Adaption is co-founded by Sara Hooker and Sudip Roy, both former leaders at Cohere and Google DeepMind veterans. Adaptive Data addresses the data challenges of modern model training by helping teams analyze dataset structure, adapt examples, evaluate quality, and export model-ready data. Adaption describes this set of capabilities as bringing data optimization techniques typically reserved for frontier labs to everyday builders, and reports an average 82% increase in data quality across early deployments.  

With this integration, Adaption users can connect their Together AI account to achieve the fastest time to high-quality, fine-tuned model through a seamless experimentation workflow.  In Adaption, the user optimizes their training dataset, then directly executes Together fine-tuning on that data with optimized hyperparameters as a starting point.  Once trained, the fine-tuned model is deployed for evaluation and eval results are shown to the user; from there, users can deploy the model on Together AI’s high-performance inference service.

Together Fine-Tuning gives Adaptive Data users the infrastructure to turn shaped datasets into stronger, more reliable open models. Its support for LoRA and full fine-tuning, large open models, and experiment visibility helps our users adapt quickly, understand what changed, and improve performance against target behaviors.
- Sara Hooker, Co-founder & CEO, Adaption 

Why Together Fine-Tuning

Together Fine-Tuning is the leading open source post-training and inference provider built for teams that want to customize leading open models to their data without managing the infrastructure themselves. Together AI 

The platform supports leading open models, including models over 100B parameters such as Kimi K2.5, GLM 5.1, or Qwen 3.5-397B, across structured tool use, reasoning, and vision-language setups. Users can fine-tune on large datasets, estimate job cost before training starts, track ETA during a run, and export models directly to Hugging Face Hub.

With this integration, datasets shaped in Adaptive Data can move directly into Together Fine-Tuning workflows. Adaptive Data improves the upstream dataset; Together Fine-Tuning turns that dataset into specialized model behavior.

Learn More

→ Read the integration announcement from Adaption

→ Read about the latest capabilities in Together Fine-Tuning

→ Read the Together Fine-Tuning docs

→ Contact Sales for fine-tuning workflows and deployment support