Note
The context length for all fine-tuning models is 8k.
The context length for all fine-tuning models is 8k.
Models for fine-tuning in Nebius Token Factory
There are different models for fine-tuning and inference. The list of models for fine-tuning includes both instruct and non-instruct models, and is categorized by provider. Deployment in Nebius Token Factory does not support all models for fine-tuning. For more information, see a list of available models.