BigMaid-20B-v1.0

Should run on 12 GB of VRAM cards in webui with context length set to 4096, ExLlamav2_HF loader and cache_8bit=True

All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:

Inference Examples

Inference API (serverless) is not available, repository is disabled.

Collection including TeeZee/BigMaid_20B_v1.0-bpw3.0-h6-exl2