Creating a 2M Parameter Thinking LLM (like o3 & DeepSeek-R1) from Scratch Using Python

From Pretraining to SFT to RLHFContinue reading on Level Up Coding »


This content originally appeared on Level Up Coding - Medium and was authored by Fareed Khan

From Pretraining to SFT to RLHF


This content originally appeared on Level Up Coding - Medium and was authored by Fareed Khan


Print Share Comment Cite Upload Translate Updates
APA

Fareed Khan | Sciencx (2025-05-19T02:46:07+00:00) Creating a 2M Parameter Thinking LLM (like o3 & DeepSeek-R1) from Scratch Using Python. Retrieved from https://www.scien.cx/2025/05/19/creating-a-2m-parameter-thinking-llm-like-o3-deepseek-r1-from-scratch-using-python/

MLA
" » Creating a 2M Parameter Thinking LLM (like o3 & DeepSeek-R1) from Scratch Using Python." Fareed Khan | Sciencx - Monday May 19, 2025, https://www.scien.cx/2025/05/19/creating-a-2m-parameter-thinking-llm-like-o3-deepseek-r1-from-scratch-using-python/
HARVARD
Fareed Khan | Sciencx Monday May 19, 2025 » Creating a 2M Parameter Thinking LLM (like o3 & DeepSeek-R1) from Scratch Using Python., viewed ,<https://www.scien.cx/2025/05/19/creating-a-2m-parameter-thinking-llm-like-o3-deepseek-r1-from-scratch-using-python/>
VANCOUVER
Fareed Khan | Sciencx - » Creating a 2M Parameter Thinking LLM (like o3 & DeepSeek-R1) from Scratch Using Python. [Internet]. [Accessed ]. Available from: https://www.scien.cx/2025/05/19/creating-a-2m-parameter-thinking-llm-like-o3-deepseek-r1-from-scratch-using-python/
CHICAGO
" » Creating a 2M Parameter Thinking LLM (like o3 & DeepSeek-R1) from Scratch Using Python." Fareed Khan | Sciencx - Accessed . https://www.scien.cx/2025/05/19/creating-a-2m-parameter-thinking-llm-like-o3-deepseek-r1-from-scratch-using-python/
IEEE
" » Creating a 2M Parameter Thinking LLM (like o3 & DeepSeek-R1) from Scratch Using Python." Fareed Khan | Sciencx [Online]. Available: https://www.scien.cx/2025/05/19/creating-a-2m-parameter-thinking-llm-like-o3-deepseek-r1-from-scratch-using-python/. [Accessed: ]
rf:citation
» Creating a 2M Parameter Thinking LLM (like o3 & DeepSeek-R1) from Scratch Using Python | Fareed Khan | Sciencx | https://www.scien.cx/2025/05/19/creating-a-2m-parameter-thinking-llm-like-o3-deepseek-r1-from-scratch-using-python/ |

Please log in to upload a file.




There are no updates yet.
Click the Upload button above to add an update.

You must be logged in to translate posts. Please log in or register.