Downloads · 30 days
15
3% of all-time downloads
LLaMA-30B-4bit-32g
Neko-Institute-of-Science/LLaMA-30B-4bit-32g
LLaMA-30B-4bit-32g is a text generation model from Neko-Institute-of-Science. Use it when you need the model to write or continue text. It is set up for transformers.
All-time downloads
546
Public
Repo size
19.4 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors19.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Apr 7, 2023
- Updated
- Apr 15, 2023
- SHA
- 96d183f7
Try a prompt
Model card
From the Hugging Face model README
30B (act-order true-sequential groupsize)
wikitext2 4.100694179534912 (stock 16bit)
wikitext2 4.179347991943359 (32g)
wikitext2 4.222894191741943 (128g)
ptb-new 8.13940715789795 (stock 16bit)
ptb-new 8.201859474182129 (32g)
ptb-new 8.227158546447754 (128g)
c4-new 6.129664421081543 (stock 16bit)
c4-new 6.190909385681152 (32g)
c4-new 6.230474948883057 (128g)
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Apr 7, 2023
- Updated
- Apr 15, 2023