Models and datasets used in the experiments reported in the paper Into The Limits of Logic: Alignment Methods for Logical Reasoning
Francisco López
Kurosawama
·
AI & ML interests
NLP, Game AI
Organizations
models 8
Kurosawama/KTO_Qwen3.5-9B
Updated
Kurosawama/KTO_DeepSeek-R1-0528-Qwen3-8B
Updated
Kurosawama/gemma-3-1b-it-LogLim
Updated
Kurosawama/Llama-3.2-3B-Instruct-LogLim
Updated
Kurosawama/Llama-3.2-3B-LogLim
Updated
Kurosawama/Llama-3.1-8B-LogLim
Updated
Kurosawama/Llama-3.1-8B-Instruct-LogLim
Updated
Kurosawama/baseline
Text Classification • 0.1B • Updated • 3
datasets 15
Kurosawama/EVAL_gemma-3-1b-it_BASE
Viewer • Updated • 609 • 7
Kurosawama/EVAL_Llama-3.2-3B-Instruct_BASE
Viewer • Updated • 609 • 5
Kurosawama/EVAL_Llama-3.2-3B_BASE
Viewer • Updated • 609 • 15
Kurosawama/EVAL_Llama-3.1-8B-Instruct_BASE
Viewer • Updated • 609 • 9
Kurosawama/EVAL_Llama-3.1-8B_BASE
Viewer • Updated • 609 • 7
Kurosawama/EVAL_gemma-3-1b-it
Viewer • Updated • 609 • 8
Kurosawama/EVAL_Llama-3.2-3B-Instruct
Viewer • Updated • 609 • 15
Kurosawama/EVAL_Llama-3.2-3B
Viewer • Updated • 609 • 8
Kurosawama/EVAL_Llama-3.1-8B-Instruct
Viewer • Updated • 609 • 6
Kurosawama/EVAL_Llama-3.1-8B
Viewer • Updated • 609 • 19