Skip to main content
Give Fireworks your data and configuration. The platform handles scheduling, training, checkpointing, and model output.

​
Methods

Supervised Fine Tuning - Text

Train text models with labeled examples of desired outputs

Supervised Fine Tuning - Vision

Train vision-language models with image and text pairs

Direct Preference Optimization

Align models with human preferences using pairwise comparisons

Reinforcement Fine Tuning

Train models using custom reward functions for complex reasoning tasks

​
Free tuning

You can tune models for free on Fireworks. Models under 16B parameters are available for free tuning—when creating a fine-tuning job in the UI, filter for free tuning models in the model selection area on the fine-tuning creation page. If kicking off jobs from the terminal, you can find the model ID from the Model Library.
When creating a fine-tuning job in the UI, look for the “Free tuning” filter in the model selection area: Free tuning filter in the model selection area

​
Supported models

Fireworks supports fine-tuning for most major open source models, including DeepSeek, Qwen, Kimi, and Llama model families, and supports fine-tuning large state-of-the-art models like Kimi K2 0905 and DeepSeek V3.1. To see all models that support fine-tuning, visit the Model Library for text models or vision models.

​
LoRA-based tuning

Managed fine-tuning uses Low-Rank Adaptation (LoRA) to fine-tune models efficiently. The fine-tuning process generates a LoRA addon — a small adapter that modifies the base model’s behavior without retraining all its weights. This approach is:
  • Faster and cheaper - Train models in hours, not days
  • Easy to deploy - Deploy LoRA addons instantly on Fireworks
  • Flexible - Run multiple LoRAs on a single base model deployment
Deprecation notice: The deployedModel request key for routing to LoRA addons is deprecated and will not be supported for any new deployments. Please migrate to the model field with the <model_name>#<deployment_name> format described in Routing requests to LoRA addons.