ModelCloud/DeepSeek-V3-0324-BF16 - Каталог нейросетей
Генерация текста

ModelCloud/DeepSeek-V3-0324-BF16

Добавлено:
ModelCloud/DeepSeek-V3-0324-BF16

This is the BF16 model of DeekSeek V3-0324. Useful for quantization and inference on GPUs that do not support FP8 (Nvidia Ampere) BF16 is result of dequantizing the FP8 quantized weights from DeepSeek AI: https://huggingface.co/deepseek-ai/DeepSeek-V3-0324 GPTQModel is your go-to choice for DeepSeek V3-0324 quantization toolkit for inference on vLLM and SGLang DeepSeek-V3-0324 demonstrates notable improvements over its predecessor, DeepSeek-V3, in several key aspects. — Significant improvements in benchmark performance: — MMLU-Pro: 75.9 → 81.2 (+5.3) — GPQA: 59.1 → 68.4 (+9.3) — AIME: 39.6 → 59.4 (+19.8) — LiveCodeBench: 39.2 → 49.2 (+10.0) — Improved the executability of the code — More aesthetically pleasing web pages and game front-ends — Enhanced style and content quality: — Aligned with the R1 writing style — Better quality in medium-to-long-form writing — Feature Enhancements — Improved multi-turn interactive rewriting — Optimized tr

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: ModelCloud
Теги: deepseek_v3, bf16, bfloat16, deepseek, v3-0324, conversational, custom_code, text-generation-inference
Лайков: 4  |  Загрузок: 73

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.