library_name: transformers | |
tags: [] | |
# Model Card for dolphin-2.9.1-llama-3-70b-<u>awq</u> | |
AWQ Quantized version of [cognitivecomputations/dolphin-2.9.1-llama-3-70b](/cognitivecomputations/dolphin-2.9.1-llama-3-70b). | |
For use with vllm and other inference engines. |