Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

DeepSeek Coder-33B Instruct

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

2K tokens

Max output length

No data

Model type

编程大模型

Release date

2023-11-01

Model file size

66GB

MoE architecture

Total params / Active params

330.0B / N/A

Knowledge cutoff

No data

DeepSeek Coder-33B Instruct

Open source & experience

Code license

MIT License

Weights license

DEEPSEEK LICENSE AGREEMENT- 免费商用授权

GitHub repo

https://github.com/deepseek-ai/DeepSeek-Coder

Hugging Face

https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct

Live demo

No live demo

DeepSeek Coder-33B Instruct

Official resources

Paper

No paper available

DataLearnerAI blog

No blog post yet

DeepSeek Coder-33B Instruct

API details

API speed

No data

No public API pricing yet.

DeepSeek Coder-33B Instruct

Benchmark Results

No benchmark data to show.

DeepSeek Coder-33B Instruct

Publisher

DeepSeek-AI

View publisher details

DeepSeek Coder-33B Instruct

Model Overview

DeepSeek Coder-33B Instruct是幻方量化旗下开源的编程大模型，这个系列的大模型包含4个版本，最小13亿参数，最高330亿参数。DeepSeek Coder-33B Instruct是其中330亿参数规模的模型。

该模型在HumanEval的评测上达到了79.3%的准确率，超过了GPT-3.5-Turbo。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送