Overview
DeepSeek developed and released the DeepSeek-R1 series, featuring multiple model sizes fine-tuned for high-performance text generation. These models are optimized for dialogue, reasoning, and information-seeking tasks, providing a balance of efficiency and accuracy while maintaining a smaller footprint compared to their original counterparts.
The DeepSeek-R1 models include distilled and full-scale variants of both Qwen and Llama architectures, catering to various applications such as customer support, conversational AI, research, and enterprise automation.
Variants
DeepSeek-R1
| No | Variant | Branch | Cortex CLI command |
|---|---|---|---|
| 1 | DeepSeek-R1-Distill-Qwen-1.5B | 1.5b | cortex run deepseek-r1:1.5b |
| 2 | DeepSeek-R1-Distill-Qwen-7B | 7b | cortex run deepseek-r1:7b |
| 3 | DeepSeek-R1-Distill-Llama-8B | 8b | cortex run deepseek-r1:8b |
| 4 | DeepSeek-R1-Distill-Qwen-14B | 14b | cortex run deepseek-r1:14b |
| 5 | DeepSeek-R1-Distill-Qwen-32B | 32b | cortex run deepseek-r1:32b |
| 6 | DeepSeek-R1-Distill-Llama-70B | 70b | cortex run deepseek-r1:70b |
Each branch contains a default quantized version:
- Qwen-1.5B: q4-km
- Qwen-7B: q4-km
- Llama-8B: q4-km
- Qwen-14B: q4-km
- Qwen-32B: q4-km
- Llama-70B: q4-km
Use it with Jan (UI)
- Install Jan using Quickstart
- Use in Jan model Hub:
cortexso/deepseek-r1
Use it with Cortex (CLI)
- Install Cortex using Quickstart
- Run the model with command:
cortex run deepseek-r1
Credits
- Author: DeepSeek
- Converter: Homebrew
- Original License: License
- Papers: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning