Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. DeepSeek-V4-Pro-0813 is the official release of DeepSeek-V4-Pro, superseding the preview version, with greatly enhanced agentic capabilities and performance improvements that are especially pronounced in production environments. It is built on the DeepSeek-V4-Pro (Preview) model structure, with a DSpark speculative decoding module attached. DeepSeek-V4-Pro-0813 outperforms DeepSeek-V4-Pro (Preview) on the benchmarks listed below, and is broadly competitive with the strongest proprietary models available. 1. For the code-agent tasks among the public benchmarks above, DeepSeek-V4-Pro-0813 is evaluated with the minimal mode of DeepSeek Harness as the agent framework, using the max reasoning effort level with temperature = 1.0, topp = 0.95`. 2. † DSBench-FullStack is an internal full-stack development test set; DSBench-Hard is an internal test set of difficult coding-agent problems. This release does not include a Jinja-format chat template. Instead, we provide a dedicated encoding folder with Python scripts and test cases demonstrating how to encode messages in OpenAI-compatible format into input…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: unsloth
Теги: deepseek_v4, unsloth, conversational, endpoints_compatible, 8-bit, fp8
Лайков: 4 | Загрузок: 816
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
