transformers
add_axk1
#46867
Merged
Overview
Commits
19
Changes
View On GitHub
Commits
  • add_axk1
    kmswin1 committed 119 days ago
  • fix TP bug of load balancing bias term
    kmswin1 committed 113 days ago
  • change default value of n_routed_experts and max_position_embeddings
    kmswin1 committed 109 days ago
  • address review comments
    kmswin1 committed 105 days ago
  • Merge remote-tracking branch 'upstream/main' into feature/add_axk1
    kmswin1 committed 104 days ago
  • change model type to snake case, and rebase
    kmswin1 committed 104 days ago
  • refactor AXK1 to inherit from deepseek_v3 and modernize config
    kmswin1 committed 92 days ago
  • address second review round: youtu-style tests, docs cleanup, inherit decoder layer
    kmswin1 committed 91 days ago
  • use Expectations class and add batched logits integration test
    kmswin1 committed 90 days ago
  • Merge branch 'main' into feature/add_axk1
    vasqu committed 90 days ago
  • fixup repo
    vasqu committed 90 days ago
  • idk why but go
    vasqu committed 90 days ago
  • Add random small model test
    kmswin1 committed 90 days ago
  • test fixes
    vasqu committed 90 days ago
  • oops that was from my local
    vasqu committed 90 days ago
  • add integration test
    kmswin1 committed 90 days ago
  • fixup integration tests
    vasqu committed 90 days ago
  • Merge branch 'main' into feature/add_axk1
    vasqu committed 90 days ago
  • style
    vasqu committed 90 days ago
FAQ Terms Privacy Refunds Impressum
Loading