Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2
Paper
•
2512.22671
•
Published
•
1
•
1
Pere Martra
oopere
AI & ML interests
Author of the Book 'Large Language Models Projects: Apply and Implement Strategies for Large Language Models' published by Apress.
Recent Activity
commented on
a paper
about 7 hours ago
Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2
updated
a model
about 8 hours ago
oopere/pruned10-llama-3.2-3B
updated
a model
about 8 hours ago
oopere/pruned20-llama-3.2-3b
Organizations
commented
a
paper
about 7 hours ago
Upload Martra_Figure_5_Prompt_Tuning.jpg
2
#5 opened almost 2 years ago
by
oopere