Peeepy

llama-33b-oasst-4bit

Peeepy/llama-33b-oasst-4bit

llama-33b-oasst-4bit is a text generation model from Peeepy. Use it when you need the model to write or continue text. It is set up for transformers.

huggyllama/llama-30b merged with serpdotai/llama-oasst-lora-30B, quantized to 4bit. 16bit and groupsize versions are on my repo as well.