guinansu
/

gptailor-llama3-8b

Text Generation

Model card Files Files and versions

GPTailor-Llama3-8B

This model is based on the paper: https://arxiv.org/pdf/2506.20480

Code: https://github.com/Guinan-Su/auto-merge-llm

Downloads last month: 3

Safetensors

Model size

6B params

Tensor type

BF16

·

Model tree for guinansu/gptailor-llama3-8b

Base model

meta-llama/Meta-Llama-3-8B

Finetuned

(494)

this model

Quantizations

Paper for guinansu/gptailor-llama3-8b

GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching

Paper • 2506.20480 • Published Jun 25, 2025 • 7