CodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.
Fine-tuningDocs | CodeQwen 1.5 7B can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model |
On-demand DeploymentDocs | On-demand deployments allow you to use CodeQwen 1.5 7B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits. |
