Training DeepSeek R1 1.5B Model for Enhanced Mathematical Reasoning Through Coldstart Method

Training DeepSeek R1 1.5B Model for Enhanced Mathematical Reasoning Through Coldstart Method

Chris Hay via YouTube Direct link

- intro

1 of 13

1 of 13

- intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Training DeepSeek R1 1.5B Model for Enhanced Mathematical Reasoning Through Coldstart Method

Automatically move to the next video in the Classroom when playback concludes

  1. 1 - intro
  2. 2 - DeepSeek R1 Chat
  3. 3 - DeepSeek R1 Ollama
  4. 4 - Think Tags
  5. 5 - Deep Seek R1 paper
  6. 6 - Generating synthetic long chains of thought
  7. 7 - Translating the CoT to natural language
  8. 8 - Self Reflection and Self Correction
  9. 9 - Generating sample data
  10. 10 - Testing the Qwen2.5-1.5B
  11. 11 - Fine Tuning Qwen2.5-1.5B with our Coldstart data
  12. 12 - Chatting with our Fine Tuned Model
  13. 13 - Conclusion

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.