DeepSeek Coder V2 Lite
deepseek-coder-v2-lite
About
DeepSeek Coder V2 Lite is an open-source Mixture-of-Experts (MoE) language model specifically tailored for efficiency and cost-effectiveness in coding tasks. It operates with a 15.7B parameter count, but only 2.4B are active at any given time, making it comparable to GPT4-Turbo for code-centric applications. This model supports 338 programming languages and has an extended context length of 128K tokens, facilitating the handling of complex codebases and lengthy prompts. Its features encompass code generation, completion, understanding, and mathematical reasoning, making it versatile for diverse coding applications. Available on Hugging Face, Ollama, and other platforms, DeepSeek Coder V2 Lite offers accessible solutions for developers and researchers, with performance that rivals or surpasses some closed-source models.
DeepSeek Coder V2 Lite has a 128K-token context window.
DeepSeek Coder V2 Lite input tokens at $0.5/1M, output at $0.5/1M.
Capabilities
Providers(1)
| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Fireworks AI | $0.5 | $0.5 | ServerlessProvisioned |
Benchmark Scores(4)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 52.4 | diamond | Open LLM Leaderboard |
| HellaSwag | 91.4 | 10-shot | Open LLM Leaderboard |
| HumanEval | 81.1 | pass@1 | Open LLM Leaderboard |
| Massive Multitask Language Understanding | 78.9 | 5-shot | Open LLM Leaderboard |
Specifications
Created by
Advancing artificial general intelligence (AGI).