huihui-ai/DeepSeek-R1-bf16

This model converted from DeepSeek-R1 to BF16. Here we simply provide the conversion command and related information about ollama. If needed, we can upload the bf16 version. 1. Download deepseek-ai/DeepSeek-R1 model, requires approximately 641GB of space. 3. Convert to BF16, requires an additional approximately 1.3 TB of space. Here, you need to download the transformation code from the «inference» folder of deepseek-ai/DeepSeek-V3 1. Use the llama.cpp conversion program to convert DeepSeek-R1-bf16 to gguf format, requires an additional approximately 1.3 TB of space. 2. Use the llama.cpp quantitative program to quantitative model (llama-quantize needs to be compiled.), other quant option. Convert first Q2_K, requires an additional approximately 227 GB of space.

Модальности:
Генерация текста

Области применения:
Диалог / чат Логика и рассуждение

Задача: Генерация текста
Автор: huihui-ai
Теги: deepseek_v3, conversational, custom_code, text-generation-inference, endpoints_compatible, fp8
Лайков: 3  |  Загрузок: 43

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.