Deepseek-Coder-7B-Instruct-v1.5 is pre-trained from Deepseek-LLM 7B on 2T tokens by employing a window size of 4K and next token prediction objective, and then fine-tuned on 2B tokens of instruction data.
Fine-tuningDocs | DeepSeek Coder 7B Instruct v1.5 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 DeepSeek Coder 7B Instruct v1.5 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits. |
