Companion models for Rearchitecting LLMs (Manning). Pruning, Distillation, Fine-Tuning, Attention Optimization & Activation Analysis for efficient SLM
Pere Martra
oopere
AI & ML interests
AI Research Engineer | Structured Pruning & LLM Efficiency | Fairness-Aware Optimization | Author “Rearchitecting LLMs” @Manning | 2K GitHub ⭐
Recent Activity
liked a model 4 days ago
oracomputing/Qwen3.8-27B-OQ3-GGUF upvoted a paper 21 days ago
BBQ: A Hand-Built Bias Benchmark for Question AnsweringOrganizations
Companion models for Rearchitecting LLMs (Manning). Pruning, Distillation, Fine-Tuning, Attention Optimization & Activation Analysis for efficient SLM
FinLLMOpt is a comprehensive collection of optimized Financial Large Language Models (FinLLMs) designed to address various tasks in the financial doma
Created by pruning the MLP (feedforward) layers, reducing the size of Llama models while improving their performance.