DeepSeek-R1 Crash Course

Learn how to use DeepSeek-R1 in this crash course for beginners. Learn about the innovative reinforcement learning approach that powers DeepSeek-R1, exploring how it achieves performance comparable to industry giants like OpenAI's o1, but at a fraction of the cost. You'll learn about its architecture, practical applications, and how to deploy this model to leverage its advanced reasoning skills for your own projects.

✏️ Course developed by Andrew Brown from @ExamProChannel .

⭐️ Contents ⭐️
00:00 Introduction
01:01 DeepSeek Overview
15:36 DeepSeek R1 via Ollama
15:36 DeepSeek R1 via LMStudio
52:12 DeepSeek via Hugging Face Transformers
1:26:06 Thoughts and Conclusions

🎉 Thanks to our Champion and Sponsor supporters:
👾 Drake Milly
👾 Ulises Moralez
👾 Goddard Tan
👾 David MG
👾 Matthew Springman
👾 Claudio
👾 Oscar R.
👾 jedi-or-sith
👾 Nattira Maneerat
👾 Justin Hual

--

[bharathnaveen]

We got the crash course right after the stock crash!

[jjones]

Wow, free code camp never fails to deliver! Thanks for this!

[LithiumBattery]

Ain’t no way you guys put up a course for deepseek already 😭😭, y’all are way too fast😩

[maxien]

This is the cyberpunk dystopia i can get behind. Open-source dystopia!

[bartlx]

14:10 You didn't activate R1's reasoning in DeepSeek's online chat. You have to click the 'DeepThink (R1)' button at the bottom of the prompt box to see it think through what you're asking.

[nike]

Deepseek shook up everyone everywhere.
Interestingly, it is from China.
Opensource Rocks!!

[yashwanth.chaudhari]

'HEY I AM ANDREW BROWN 'will be my New Ringtone.Hats off to this guy.He is not pregnant but still delivers the quickest.

[KottaKotta-zn]

Best free course for the the tech enthusiastic

[asbjo]

I am just an AI novice, only just playing around with some small models thdt are able to run on my amd R7 8845hs with 16gb ram. But Deepseek is thoroughly impressive compared to Phi-3 and other tiny models. The response and understanding of sytem message and conversational output it provides is way, way ahead of sll the other small models ive tried (only a few). I can actually see me using it for something useful!! That is crazy. And the july 2024 knowledge cutoff is great! Recent enough to be useful for other things than historical information.
It is massively slower to think and respond, but the insigt to it thoughts are massively useful!

[Random.-ic]

One of the best learning YT channels for free. Love your long form, well detailed explanation videos.

[salvadorzorraquin]

bro I was screaming there was a Japanese option, glad you relized

[Isreal_m]

My most loved YouTube channel and community.... Thank you guys for this course ... Freecodecamp rocks all the way..

[NatividadMcintyre]

Thanks for the XAI910K update! I am loving my XAI910K!

[minchin]

Great job your videos never disappoint!

[jobafemi]

The pace and quality you bring to the table!!!!

[OzenEbru-orge]

Just recently joining in on the fun with the XAI910K gang. Been liking the content, good job ☕️

[amjads]

This is so basic and now there is a course for this, superb

[rakohasan]

We felt deepSeek fever! You jumped with desirable video.thank you.

[AyliaAhmet]

XAI910K is on a category of its own: a fast POW, with an impressive consensus mechanism.

[isma-bjuo]

That's why you're the best 🔥😊 #freecodecamp