JonasGeiping/cramming
Cramming the training of a (BERT-type) language model into limited compute.
PythonMIT
Watchers
- a2un@IITH
- Amirtmgr
- christopherok
- corranmac
- drkostasUniversity of Tennessee, Knoxville
- eemailme
- JonasGeipingELLIS Institute & MPI-IS Tübingen
- jullyanolinoENAP
- MaximeVandegarSLAC, Stanford University
- michalwolsNew York
- nshmyrevAlpha Cephei Inc
- rishikksh20Dubpro.ai
- sheshuguang
- shmuhammadd
- symbiote-researchSymbiote AI
- tiendung
- vgoklaniNew York, NY
- voxmenthe
- vujadinGameStudioHx
- WilliamTambelliniRWS
- wx-bRIOS
- yotamnahum@Samplead