Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2
Paper
•
2512.22671
•
Published
•
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
authored
a paper
3 days ago
Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2
commented on
a paper
4 days ago
Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2
updated
a model
4 days ago
oopere/pruned10-llama-3.2-3B
Organizations
upvoted
a
paper
4 days ago
upvoted
an
article
about 2 months ago
Article
Making LLMs Smaller Without Breaking Them: A GLU-Aware Pruning Approach
•
15
upvoted
2
articles
6 months ago
Article
Good answers are not necessarily factual answers: an analysis of hallucination in leading LLMs
•
42
Article
LLMs recognise bias but also reproduce harmful stereotypes: an analysis of bias in leading LLMs
•
16
upvoted
an
article
7 months ago
Article
Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM
- +2
•
480
upvoted
an
article
10 months ago
Article
Training a Gemma 2 2B-IT for Reasoning with GRPO
•
6
upvoted
an
article
11 months ago
Article
Open-R1: a fully open reproduction of DeepSeek-R1
- +1
•
887
upvoted
a
paper
about 1 year ago
upvoted
2
articles
over 1 year ago
Article
Preference Tuning LLMs with Direct Preference Optimization Methods
- +3
•
75
Article
How NuminaMath Won the 1st AIMO Progress Prize
- +6
•
124
upvoted
a
collection
over 1 year ago
upvoted
2
articles
over 1 year ago
Article
🪆 Introduction to Matryoshka Embedding Models
- +1
•
185
Article
Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
- +3
•
171