Downloads · 30 days
12
5% of all-time downloads
Llama-3-Taiwan-70B-Instruct-fp8
minyichen/Llama-3-Taiwan-70B-Instruct-fp8
Llama-3-Taiwan-70B-Instruct-fp8 is a text generation model from minyichen. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.
- Model creator: Yen-Ting Lin - Original model: Llama-3-Taiwan-70B-Instruct
All-time downloads
240
Public
Parameters
70.6B
72.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors72.7 GB · 100%
Parameter types
How the weights are stored.
F8_E4M368.5B · 97%
Base models
Model card
From the Hugging Face model README
Llama-3-Taiwan-70B-Instruct-fp8
- Model creator: Yen-Ting Lin
- Original model: Llama-3-Taiwan-70B-Instruct
Description
This repo contains fp8 model files for Llama-3-Taiwan-70B-Instruct.
<!-- description end --> <!-- repositories-available start --> <!-- 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.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- llama3
- Languages
- zh, en
- Created
- Aug 1, 2024
- Updated
- Aug 1, 2024