Cette page est affichée en anglais. Une traduction française est en cours.
May 8, 2026·1 min de lecture

DeepSeek Coder — Code-Specialized Model for Local Inference

DeepSeek Coder is the code-specialized open-weight model with FIM (fill-in-middle) support. Beats Codestral on HumanEval. Drops into Continue, Aider.

Anonymous
Anonymous · Community
Prêt pour agents

Staging sûr pour cet actif

Cet actif est d'abord staged. Le prompt copié demande à l'agent d'inspecter les fichiers staged avant d'activer scripts, config MCP ou config globale.

Stage only · 27/100Policy : staging
Surface agent
Tout agent MCP/CLI
Type
Knowledge
Installation
Stage only
Confiance
Confiance : Community
Point d'entrée
Asset
Commande de staging sûr
npx -y tokrepo@latest install 08acf3a7-b56b-40d2-9c94-9a8eb773eca4 --target codex

Stage les fichiers d'abord; l'activation exige la revue du README et du plan staged.

DeepSeek Coder is the code-specialized open-weight model with FIM (fill-in-middle) support. Beats Codestral on HumanEval. Drops into Continue, Aider.

Fil de discussion

Connectez-vous pour rejoindre la discussion.
Aucun commentaire pour l'instant. Soyez le premier à partager votre avis.

Actifs similaires

DeepSeek-R1 — Open-Weight Reasoning Model Rivaling OpenAI o1

DeepSeek-R1 is the open-weight reasoning model that matches OpenAI o1 on math, code, science benchmarks. Streaming chain-of-thought visible. MIT-licensed.

Knowledge
DeepSeek

DeepSeek-V3 — Open-Weight 671B MoE Model with GPT-4o Quality

DeepSeek-V3 is a 671B-param MoE model (37B active per token). Matches GPT-4o on benchmarks. MIT-licensed weights, $0.27/1M input on the hosted API.

Knowledge
DeepSeek

ds4 — DeepSeek Local Inference Engine by antirez

A minimal C-based local inference engine for DeepSeek 4 Flash, optimized for Apple Metal and NVIDIA CUDA, created by the author of Redis.

Configs
AI Open Source

Unsloth — 2x Faster Local LLM Training & Inference

Unsloth is a unified local interface for running and training AI models. 58.7K+ GitHub stars. 2x faster training with 70% less VRAM across 500+ models including Qwen, DeepSeek, Llama, Gemma. Web UI wi

Skills
AI Open Source
◈Accueil🔍Rechercher👤Moi