Modelpublic

CALISTA-INDUSTRY/DeepSeek-R1-Distill-Qwen-1.5B-FineTune

sourceHugging Facemitupdated 2y agoView on Hugging Face

0likes32downloads

Model Card

DeepSeek-R1 Release __________________________________________________________________________________________

⚡ Performance on par with OpenAI-o1

📖 Fully open-source model & technical report

🏆 MIT licensed: Distill & commercialize freely!

🌐 Website & API are live now! Try DeepThink at chat.deepseek.com today! __________________________________________________________________________________________

🔥 Bonus: Open-Source Distilled Models!

🔬 Distilled from DeepSeek-R1, 6 small models fully open-sourced

📏 32B & 70B models on par with OpenAI-o1-mini

🤝 Empowering the open-source community

🌍 Pushing the boundaries of open AI! _____________________________________________________________________

🛠️ DeepSeek-R1: Technical Highlights

📈 Large-scale RL in post-training

🏆 Significant performance boost with minimal labeled data

🔢 Math, code, and reasoning tasks on par with OpenAI-o1

📄 More details: https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeekR1.pdf ____________________________________________________________________

🌐 API Access & Pricing

⚙️ Use DeepSeek-R1 by setting model=deepseek-reasoner

💰 $0.14 / million input tokens (cache hit)

💰 $0.55 / million input tokens (cache miss)

💰 $2.19 / million output tokens

📖 API guide: https://api-docs.deepseek.com/guides/reasoning_model