Engy is an AI-powered development tool that generates fully functional web applications from natural language, streamlining the process from idea to working prototype.
-
Updated
Mar 18, 2025 - Python
#
gpt-o1
Here are 3 public repositories matching this topic...
Lightweight replication study of DeepSeek-R1-Zero. Interesting findings include "No Aha Moment", "Longer CoT ≠ Accuracy", and "Language Mixing in Instruct Models".
reinforcement-learning fine-tuning post-training llm deepseek gpt-o1 reasoning-language-models reasoning-models deepseek-r1
-
Updated
Apr 1, 2025 - Python
Pure RL to post-train base models for social reasoning capabilities. Lightweight replication of DeepSeek-R1-Zero with Social IQa dataset.
reinforcement-learning fine-tuning post-training llm deepseek gpt-o1 reasoning-language-models reasoning-models deepseek-r1
-
Updated
Mar 16, 2025 - Python
Improve this page
Add a description, image, and links to the gpt-o1 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the gpt-o1 topic, visit your repo's landing page and select "manage topics."