Readme
See the official model card for this model here: https://huggingface.co/TheBloke/Llama-2-70B-chat-AWQ
Thank you to TheBloke for sharing this model!
nateraw
/
llama-2-70b-chat-awq
llama-2-70b-chat quantized with AWQ and served with vLLM
Run time and cost
This model costs approximately $0.22 to run on Replicate, or 4 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 4 minutes. The predict time for this model varies significantly based on the inputs.