Picture for Michael Santacroce

Michael Santacroce

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Apr 23, 2024
Viaarxiv icon

Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences

Add code
Apr 04, 2024
Figure 1 for Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Figure 2 for Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Figure 3 for Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Figure 4 for Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Viaarxiv icon

Adapting LLM Agents Through Communication

Add code
Oct 10, 2023
Figure 1 for Adapting LLM Agents Through Communication
Figure 2 for Adapting LLM Agents Through Communication
Figure 3 for Adapting LLM Agents Through Communication
Figure 4 for Adapting LLM Agents Through Communication
Viaarxiv icon

Efficient RLHF: Reducing the Memory Usage of PPO

Add code
Sep 01, 2023
Figure 1 for Efficient RLHF: Reducing the Memory Usage of PPO
Figure 2 for Efficient RLHF: Reducing the Memory Usage of PPO
Figure 3 for Efficient RLHF: Reducing the Memory Usage of PPO
Figure 4 for Efficient RLHF: Reducing the Memory Usage of PPO
Viaarxiv icon

What Matters In The Structured Pruning of Generative Language Models?

Add code
Feb 07, 2023
Figure 1 for What Matters In The Structured Pruning of Generative Language Models?
Figure 2 for What Matters In The Structured Pruning of Generative Language Models?
Figure 3 for What Matters In The Structured Pruning of Generative Language Models?
Figure 4 for What Matters In The Structured Pruning of Generative Language Models?
Viaarxiv icon