今天，全球首个在代码、数学能力上与GPT-4-Turbo争锋的模型，DeepSeek-Coder-V2，正式上线和开源。
28 个赞
Silicon上能用吗
4 个赞
挺强的，略微体验了一下确实逻辑能力不错
4 个赞
多少钱啊
4 个赞
这么牛
3 个赞
Ollama估计过几天就上线了，现在还没有coder版本
之前没出二代时候，始皇就推荐用deepseek-coder做代码补全
卧槽，太香了
这次是甚至可以替代chat了，而非只能补全
1 个赞
这个coder也是236b啊 
尝试在三级区白嫖的英特尔试试？不过不支持cuda，不知道能部署不，还不如直接买官方的
api 版本上下文还是 32k，期待上新 128k 版本
This performance is notable as it breaks the dominance typically seen from closed-source models, standing out as a leading open-source contender. It is surpassed only by GPT-4o, which leads with an average score of 76.4%. DeepSeek-Coder-V2-Instruct shows top-tier results across a variety of languages, including the highest scores in Java and PHP, and strong performances in Python, C++, C#, TypeScript, and JavaScript, underscoring its robustness and versatility in handling diverse coding challenges.
1 个赞
期待deepseek-math也更新！
这次的coder-v2使用的训练方法与deepseek-math是相同的，可以说是math的整合版
To collect code-related and math-related web texts from Common Crawl, we follow the same pipeline as DeepSeekMath(Shao et al., 2024).
5 个赞
谢谢！！！
数学能力是相当不错的，虽然只有10%的数学语料
The pre-training data for DeepSeek-Coder-V2 primarily consists of 60% source code, 10% math corpus, and 30% natural language corpus.
The results, presented in Table 9, were obtained using greedy decoding without the aid of tools or voting techniques, unless otherwise specified. DeepSeek-Coder-V2 achieved an accuracy of 75.7% on the MATH benchmark and 53.7% on Math Odyssey, comparable to the state-of-the-art GPT-4o. Additionally, DeepSeek-Coder-V2 solves more problems from AIME2024 than the other models, demonstrating its strong mathematical reasoning capabilities.
可以看看deepseek会不会用v2架构更新math模型
4 个赞
太好了，高考题启动！
可能拿高考题训练了hhhh
1 个赞
支持开源！
1 个赞