DeepSpeed
Add the policy to run llama model from the official repo
#4313
Merged
Overview
Commits
19
Changes
View On GitHub
Commits
  • Add the llama2 support from the official llama repo
    Reza Yazdani committed 2 years ago
  • add back commented function
    Reza Yazdani committed 2 years ago
  • add new policy & implementation for llama2
    Reza Yazdani committed 2 years ago
  • add some changes to inject/run the 70b llama model
    Reza Yazdani committed 2 years ago
  • remove debugging code
    Reza Yazdani committed 2 years ago
  • remove more debugging code
    Reza Yazdani committed 2 years ago
  • Merge branch 'master' into add-llama2-support
    RezaYazdaniAminabadi committed 2 years ago
  • formatting
    mrwyattii committed 2 years ago
  • Merge branch 'master' into add-llama2-support
    RezaYazdaniAminabadi committed 2 years ago
  • Merge branch 'master' into add-llama2-support
    mrwyattii committed 2 years ago
  • Merge branch 'master' into add-llama2-support
    RezaYazdaniAminabadi committed 2 years ago
  • use num_kv only when it has positive value
    Reza Yazdani committed 2 years ago
  • Merge branch 'add-llama2-support' of github.com:microsoft/DeepSpeed into add-llama2-support
    Reza Yazdani committed 2 years ago
  • use the num_kv param only if it is positive
    Reza Yazdani committed 2 years ago
  • Merge branch 'master' into add-llama2-support
    awan-10 committed 2 years ago
  • fix syntax and format errors.
    awan-10 committed 2 years ago
  • fix an issue with the float32 transform kernel
    Reza Yazdani committed 2 years ago
  • Merge branch 'add-llama2-support' of github.com:microsoft/DeepSpeed into add-llama2-support
    Reza Yazdani committed 2 years ago
  • Merge branch 'master' into add-llama2-support
    RezaYazdaniAminabadi committed 2 years ago
FAQ Terms Privacy Refunds Impressum
Loading