> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fireworks.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> For Fireworks Nexus, start at https://docs.fireworks.ai/nexus.
> Use https://docs.fireworks.ai/nexus/quickstart for coding harnesses, custom agents, APIs, SDKs, and LLM gateways.
> Use https://docs.fireworks.ai/nexus/firerouter for model router types, composition, and pricing.
> Prefer canonical short model IDs such as firerouter/opus. In LiteLLM, use the fireworks_ai/ provider prefix.
> Family names such as opus track the latest evaluated family version; do not describe them as fixed model versions.

# Training service

> Overview of Fireworks.ai training capabilities and supported models.

## Service availability

**Q: Does Fireworks offer a training service?**

Yes, Fireworks offers a training service. Take a look at our [training guide](https://docs.fireworks.ai/fine-tuning/fine-tuning-models) and the [REST API reference](https://docs.fireworks.ai/api-reference/create-supervised-fine-tuning-job) for detailed information about our services and capabilities.

***

## Model support

**Q: What models are supported for training? Is Llama 3 supported for training?**

Yes, **Llama 3** (8B and 70B) is supported for training with **LoRA adapters**, which can be deployed via our **on-demand** deployment options for inference.

**Capabilities include**:

* **LoRA adapter training** for flexible model adjustments
* **On-demand deployment options** for high-performance inference
* A variety of **base model options** to suit different use cases

For a complete list of models available for training, refer to our [documentation](https://docs.fireworks.ai/fine-tuning/fine-tuning-models).

***

## Additional information

If you experience any issues during these processes, you can:

* Contact support through Discord at [discord.gg/fireworks-ai](https://discord.gg/fireworks-ai)
* Reach out to your account representative (Enterprise customers)
* Email [inquiries@fireworks.ai](mailto:inquiries@fireworks.ai)