Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese. deepseek-coder-33b-instruct is a 33B parameter model initialized from deepseek-coder-33b-base and fine-tuned on 2B tokens of instruction data.
DeepSeek Coder 33B Instruct can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model
Learn MoreOn-demand deployments give you dedicated GPUs for DeepSeek Coder 33B Instruct using Fireworks' reliable, high-performance system with no rate limits.
Learn MoreDeepseek
16384
Available
$0.9
