Hugging Face's logo

CalderaAI
/
13B-Ouroboros-GPTQ4bit-128g-CUDA

Text Generation
Transformers
PyTorch
English
llama
alpaca
vicuna
uncensored
Merge
mix
airoboros
openorca
orcamini
orca
instruct
mixtune
GPTQ
quantized
4bit
cuda
text-generation-inference
Model card Files Community

GPTQ 4 bit 128 groupsize CUDA quantization of CalderaAI's 13B Ouroboros:

https://huggingface.co/CalderaAI/13B-Ouroboros

Downloads last month
21
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Datasets used to train CalderaAI/13B-Ouroboros-GPTQ4bit-128g-CUDA