---
base_model: yentinglin/Llama-3-Taiwan-70B-Instruct
language:
- zh
- en
license: llama3
model_creator: yentinglin
model_name: Llama-3-Taiwan-70B-Instruct
model_type: llama
pipeline_tag: text-generation
quantized_by: minyichen
tags:
- llama-3
---

# Llama-3-Taiwan-70B-Instruct-fp8
- Model creator: [Yen-Ting Lin](https://huggingface.co/yentinglin)
- Original model: [Llama-3-Taiwan-70B-Instruct](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct)

<!-- description start -->
## Description

This repo contains fp8 model files for [Llama-3-Taiwan-70B-Instruct](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct).

<!-- description end -->
<!-- repositories-available start -->
* [GPTQ models for GPU inference](https://huggingface.co/minyichen/Llama-3-Taiwan-70B-Instruct-GPTQ)
* [Yen-Ting Lin's original unquantized  model](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct)
<!-- repositories-available end -->

## Quantization parameter

- activation_scheme : static
- quant_method : fp8
- ignored_layers : lm_head

It tooks about 8.5 hrs to quantize on H100.