llama.cpp
model : add BailingMoeV2 support
#16063
Merged
Overview
Commits
22
Changes
View On GitHub
Commits
  • add BailingMoeV2 support
    CISC committed 1 year ago
  • update llm types
    CISC committed 1 year ago
  • undo
    CISC committed 1 year ago
  • undo
    CISC committed 1 year ago
  • update llm types
    CISC committed 1 year ago
  • add model collection link
    CISC committed 1 year ago
  • update
    CISC committed 1 year ago
  • Merge branch 'master' into cisc/bailingmoe2
    CISC committed 360 days ago
  • almost working
    CISC committed 355 days ago
  • Merge branch 'master' into cisc/bailingmoe2
    CISC committed 355 days ago
  • correct group selection and rename n_group_exp
    CISC committed 354 days ago
  • avoid large top_k and use argmax instead for now
    CISC committed 354 days ago
  • poke
    CISC committed 353 days ago
  • Merge branch 'master' into cisc/bailingmoe2
    CISC committed 353 days ago
  • Merge branch 'master' into cisc/bailingmoe2
    CISC committed 346 days ago
  • Merge branch 'master' into cisc/bailingmoe2
    CISC committed 343 days ago
  • skip group selection when there are no tokens
    CISC committed 338 days ago
  • fix 1T conversion
    CISC committed 336 days ago
  • hopefully fixed expert group selection
    CISC committed 336 days ago
  • make expert group selection generally available
    CISC committed 334 days ago
  • allow n_expert_groups to be 1 (Kimi K2) [no ci]
    CISC committed 334 days ago
  • address review suggestions
    CISC committed 332 days ago
FAQ Terms Privacy Refunds Impressum
Loading