search

NolanoOrg / cformers

SoTA Transformers with C-backend for fast inference on your CPU.
MIT License
311 stars 29 forks source link

Add GPT-NeoX, all pythia models and Open-Chat-Kit's GPT NeoX #15

Open Ayushk4 opened 1 year ago

Ayushk4 commented 1 year ago

Refer #11 for instructions.

Note: the feature for use_parallel_residual = false in config needs to be sanity checked.