deepseek
Original：🇺🇸 English
Translated
DeepSeek AI models for coding. Use for code AI.
1installs
Sourceg1joshi/agent-skills
Added on
NPX Install
npx skill4agent add g1joshi/agent-skills deepseekTags
Translated version includes tags in frontmatterSKILL.md Content
View Translation Comparison →DeepSeek
DeepSeek (from China) disrupted the market in late 2024/2025 by releasing DeepSeek-V3 and R1 (Reasoning) with performance matching Claude/GPT-4 at 1/10th the cost.
When to Use
- Cost Efficiency: The API is incredibly cheap.
- Reasoning: DeepSeek-R1 uses Chain-of-Thought reinforcement learning (like OpenAI o1) but is open weights.
- Coding: DeepSeek-Coder-V2 is a top-tier coding model.
Core Concepts
MLA (Multi-Head Latent Attention)
Architectural innovation that drastically reduces KV cache memory usage (allowing huge context).
DeepSeek-R1
A reasoning model that outputs its "thought process" before the final answer.
Best Practices (2025)
Do:
- Use R1 for Math/Logic: It rivals o1-preview in math benchmarks.
- Local Distillations: Run locally for private reasoning.
DeepSeek-R1-Distill-Llama-70B
Don't:
- Don't suppress thoughts: When using R1, the "thought" trace is valuable for debugging the model's logic.