DeepSeek Coder V2 Lite Instruct is a 16-billion-parameter open-source Mixture-of-Experts (MoE) code language model with 2.4 billion active parameters, developed by DeepSeek AI. Fine-tuned for instruction following, it achieves performance comparable to GPT4-Turbo on code-specific tasks. Pre-trained on an additional 6 trillion tokens, it enhances coding and mathematical reasoning capabilities, supports 338 programming languages, and extends context length from 16K to 128K while maintaining strong general language performance.
Fine-tuningDocs | DeepSeek Coder V2 Lite Instruct 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 V2 Lite Instruct on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits. |
DeepSeek Coder V2 Lite Instruct is a 16B parameter open-source Mixture-of-Experts (MoE) code language model developed by DeepSeek AI. It uses 2.4B active parameters and is fine-tuned for instruction following. It was built upon DeepSeek V2 and further pre-trained with an additional 6 trillion tokens for enhanced coding and math reasoning capabilities.
The model is optimized for:
It supports 338 programming languages and performs competitively with GPT-4 Turbo on code-specific benchmarks.
The maximum context length for this model is 128K tokens.
No, function calling is not supported for this model.
The model has 16B total parameters with 2.4B active parameters (Mixture-of-Experts).
Yes. Fireworks supports LoRA-based fine-tuning for this model.
The model is licensed under the DeepSeek Model License, with the codebase under MIT License, and commercial use is permitted under the Model License.
