Downloads · 30 days
10
10% of all-time downloads
Llama3-Taiwan-70B-Instruct-128K-AWQ-4bits
aqweteddy/Llama3-Taiwan-70B-Instruct-128K-AWQ-4bits
Llama3-Taiwan-70B-Instruct-128K-AWQ-4bits is a text generation model from aqweteddy. 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.
Llama3-Taiwan-70B-Instruct-128K-AWQ-4bits leverages 4-bit quantized weights, processed with AutoAWQ, to significantly reduce GPU memory requirements.
All-time downloads
98
Public
Parameters
70.6B
39.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors39.8 GB · 100%
Parameter types
How the weights are stored.
I3268.5B · 97%
Model card
From the Hugging Face model README
Llama3-Taiwan-70B-Instruct-128K-AWQ-4bits leverages 4-bit quantized weights, processed with AutoAWQ, to significantly reduce GPU memory requirements.
References
For more information and detailed documentation, please refer to the links provided.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- llama3
- Languages
- zh, en
- Created
- Jul 12, 2024
- Updated
- Jul 12, 2024