DeepSeek R1 Explained: How did Chain of Thought, Reinforcement Learning & Model Distillation help?

[@RagnarPitla]

Thank you for watching my video! You can find the GitHub links in the description below and right here. Wishing you a fantastic day! Don’t forget to join me on KZbin for more content. www.youtube.com/@RagnarPitla?sub_confirmation=1 Deepseek Hugging Face: huggingface.co/deepseek-ai Github: github.com/deepseek-ai/DeepSeek-R1 Deepseek V3: github.com/deepseek-ai/DeepSeek-V3

[@Tamara-Jost]

Thank you for this „scientific“ explanation. It is really helpful! Looking forward to your video on finetuning

[@RagnarPitla]

Thanks so much, Tamar! I know it’s a bit political too, but my goal is to understand how they achieved it. Learning from their approach can help us apply similar strategies while ensuring ethical use through proper licensing or open research models.

[@SalmanZaidiB96]

Ah, was searching through all the content for a Rag tech update!

[@YCB-in7sf]

Waiting for another video on deepseek

[@RagnarPitla]

haha! i feel you. We all have our views but I know its the hot topic and even I had to learn and reaserch to Know how they did it.

[@passage2enBleu]

My comment disappeared.

[@RagnarPitla]

I did have your previous message in below!