A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token from Deepseek. Updated checkpoint. Note that fine-tuning for this model is only available upon request through contacting fireworks at https://fireworks.ai/company/contact-us.
On-demand DeploymentDocs | On-demand deployments allow you to use Deepseek V3 03-24 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits. |
