Skip to content

0.14.0
Compare
Choose a tag to compare
@matatonic matatonic released this 19 May 00:55
· 122 commits to main since this release
0.14.0
e839f11

Recent updates

Version: 0.14.0

  • docker-compose.yml: Assume the runtime supports the device (ie. nvidia)
  • new model support: qihoo360/360VL-8B, qihoo360/360VL-70B (70B loading error, see note, also too large for me to test because 4bit & 8bit are also not working for me - hopefully a quantized model comes out soon)
  • new model support: BAAI/Emu2-Chat, Can be slow to load, may need --max-memory option control the loading on multiple gpus
  • new model support: TIGER-Labs/Mantis: Mantis-8B-siglip-llama3, Mantis-8B-clip-llama3, Mantis-8B-Fuyu
Assets 2
Loading