This is a base model trained for raw text prediction, not instruction-following. Prompts should be written as examples, not simple requests.

Favicon de deepseek

DeepSeek: DeepSeek V3.1 Base

deepseek/deepseek-v3.1-base

Poids du modèle

This is a base model, trained only for raw next-token prediction. Unlike instruct/chat models, it has not been fine-tuned to follow user instructions. Prompts need to be written more like training text or examples rather than simple requests (e.g., “Translate the following sentence…” instead of just “Translate this”).

DeepSeek-V3.1 Base is a 671B parameter open Mixture-of-Experts (MoE) language model with 37B active parameters per forward pass and a context length of 128K tokens. Trained on 14.8T tokens using FP8 mixed precision, it achieves high training efficiency and stability, with strong performance across language, reasoning, math, and coding tasks.

Modalités
Contexte
164K
Publié
20 août 2025
Date limite des connaissances
mars 2025

Activité

Volume de jetons et trafic des requêtes vers ce modèle au fil du temps.

Actuellement indisponible via le routage dans la région UE. Documentation sur le routage intrarégional

Questions fréquentes

Explorer d’autres modèles