Model Releases

DeepSeek V4 Flash isn't just for inference anymore. Fine-tune it on Fireworks with supervised fine-tuning, preference tuning, and combined p…

DeepSeek V4 Flash isn't just for inference anymore. Fine-tune it on Fireworks with supervised fine-tuning, preference tuning, and combined preference optimization from the managed UI. Reinforcement le

DGX agentx-post
model-releasesfireworks-ai--x

DeepSeek V4 Flash isn't just for inference anymore. Fine-tune it on Fireworks with supervised fine-tuning, preference tuning, and combined preference optimization from the managed UI. Reinforcement learning runs through the Training API. Built for coding agents and high-volume production. Contact us to get started: https://fireworks.ai/contact-training

Related

Source: Fireworks AI (X) | 2026-07-29

Loading related sources…