NewJoin us for our inaugural conference, Forge 2026
DocsLog inGet started
Fireworks logo

DeepSeek Coder V2 Lite Instruct

Ready
model path:accounts/fireworks/models/deepseek-coder-v2-lite-instruct
Deploy on demand

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.

DeepSeek Coder V2 Lite Instruct API Features

On-demand Deployment

Docs

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.

Metadata

State
Ready
Created on
4 JUL, 2024
Kind
Base model
Provider
Fireworks
Huggingface
DeepSeek/deepseek-coder-v2-lite-instruct

Specifications

Calibrated
Yes
Mixture-of-Experts
Yes
Parameters
15.7B

Supporting Functionality

Fine-tuning
Not Supported
Serverless
Not Supported
Context Length
163k tokens
Function Calling
Not Supported
Embeddings
Not Supported
Rerankers
Not Supported
Supporting image input
Not Supported

DeepSeek Coder V2 Lite Instruct FAQs

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.