
DeepSeek-V3
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. - Outil IA intelligent pour améliorer votre productivité.


DeepSeek's first-generation reasoning models. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning without supervised fine-tuning, demonstrated remarkable performance on reasoning. - Outil IA intelligent pour améliorer votre productivité.
1
Views
0
Likes
Jan 2026
Added
github.com
Website
DeepSeek's first-generation reasoning models. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning without supervised fine-tuning, demonstrated remarkable performance on reasoning.
DeepSeek-R1 est un excellent outil dans la catégorie open-source-llm, adapté à tous les utilisateurs ayant besoin d'une assistance IA.
Visit the official website to get started
Have an AI tool to share?
Submit Your Tool
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. - Outil IA intelligent pour améliorer votre productivité.

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud. - Outil IA intelligent pour améliorer votre productivité.

Llama3 is a large language model developed by Meta AI. It is the successor to Meta's Llama2 language model. - Outil IA intelligent pour améliorer votre productivité.

Mixtral 8x7B, a high-quality sparse mixture of experts model (SMoE) with open weights. Mixtral outperforms Llama 2 70B on most benchmarks with 6x faster inference. - Outil IA intelligent pour améliorer votre productivité.