— Model Architecture: DeepSeek-V2.5-1210 — Input: Text — Output: Text — Model Optimizations: — Weight quantization: FP8 — Activation quantization: FP8 — Release Date: 3/1/2025 — Version: 1.0 — Model Developers: Neural Magic Quantized version of DeepSeek-V2.5-1210. It achieves an average score of 77.8 on the OpenLLM benchmark (version 1), whereas the unquantized model achieves 77.82. This model was obtained by quantizing the weights and activations to FP8 data type, ready for inference with vLLM >= 0.5.2. This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. The weights and activations of the linear operators within transformers blocks are quantized, except the MLP routers. This model can be deployed efficiently using the vLLM backend, as shown in the example below. vLLM also supports OpenAI-compatible serving. See the documentation for more details. This model was created with llm-compressor by running the code snippet below with the following command: The model was evaluated on OpenLLM Leaderboard V1 using the following command:
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: RedHatAI
Теги: deepseek_v2, moe, fp8, vllm, conversational, custom_code, en, text-generation-inference
Лайков: 4 | Загрузок: 34,039
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.