Downloads · 30 days
188
14% of all-time downloads
llama-30b-supercot-4bit-128g-cuda
tsumeone/llama-30b-supercot-4bit-128g-cuda
llama-30b-supercot-4bit-128g-cuda is a text generation model from tsumeone. Use it when you need the model to write or continue text. It is set up for transformers.
Quantized version of this: https://huggingface.co/ausboss/llama-30b-supercot
All-time downloads
1.3K
Public
Repo size
18.1 GB
Likes
25
Public
Repo makeup
Click a slice to open those files.
.safetensors18.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Apr 21, 2023
- Updated
- Apr 23, 2023
- SHA
- 41ae1948
Try a prompt
Model card
From the Hugging Face model README
Quantized version of this: https://huggingface.co/ausboss/llama-30b-supercot
GPTQ quantization using https://github.com/0cc4m/GPTQ-for-LLaMa for compatibility with 0cc4m's fork of KoboldAI
Command used to quantize:
python llama.py c:\llama-30b-supercot c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors 4bit-128g.safetensors
Evaluation & Score (Lower is better):
- WikiText2: 4.51
- PTB: 17.46
- C4: 6.37
Non-groupsize version is here: https://huggingface.co/tsumeone/llama-30b-supercot-4bit-cuda
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Apr 21, 2023
- Updated
- Apr 23, 2023