2 16 140

PeijieDong

pprp

https://pprp.github.io

AI & ML interests

Model Compression; Large Language Model;

Organizations

None yet

pprp's activity

upvoted a paper 24 days ago

Should We Really Edit Language Models? On the Evaluation of Edited Language Models

Paper • 2410.18785 • Published 24 days ago • 5

upvoted 6 papers about 1 month ago

FlatQuant: Flatness Matters for LLM Quantization

Paper • 2410.09426 • Published Oct 12 • 12

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Paper • 2410.10819 • Published Oct 14 • 6

LPZero: Language Model Zero-cost Proxy Search from Zero

Paper • 2410.04808 • Published Oct 7 • 2

Benchmarking Agentic Workflow Generation

Paper • 2410.07869 • Published Oct 10 • 25

PrefixQuant: Static Quantization Beats Dynamic through Prefixed Outliers in LLMs

Paper • 2410.05265 • Published Oct 7 • 29

LongGenBench: Long-context Generation Benchmark

Paper • 2410.04199 • Published Oct 5 • 17

upvoted an article 3 months ago

Article

LLM Data Engineering 3——Data Collection Magic: Acquiring Top Training Data

•

Jun 4

• 4

upvoted a collection 4 months ago

Google Gemma2

Collection

24 items • Updated 26 days ago • 14

upvoted an article 4 months ago

Article

Welcome Gemma 2 - Google's new open LLM

Jun 27

• 123

upvoted a collection 4 months ago

🪐 SmolLM

Collection

A series of smol LLMs: 135M, 360M and 1.7B. We release base and Instruct models as well as the training corpus and some WebGPU demos • 12 items • Updated Aug 18 • 197

upvoted a paper 4 months ago

Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models

Paper • 2406.02924 • Published Jun 5 • 2

upvoted an article 6 months ago

Article

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

May 24, 2023

• 91

upvoted a paper 9 months ago

Shortened LLaMA: A Simple Depth Pruning for Large Language Models

Paper • 2402.02834 • Published Feb 5 • 14

upvoted a collection 10 months ago

Model Merging

Collection

Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! • 30 items • Updated Jun 12 • 217