directly use bool instead of torch.float16 to avoid crash in ASIC like HPU which does not support float16

LLM-foundry update June 16, 2023 22:55:57 (#63)

add explicit cast where running without autocast causes issues (#60)

add text-generation pipeline example with autocast (#59)

Update modeling_mpt.py (#55)

Change `wte` to use shared embedding (#56)

Add custom embedding (#53)

LLM Foundry Updates 06-01-2023 (#47)

Update modeling_mpt.py (#45)

Update README.md

Add eos_token_id to generation config (#26)

updt flash_attn_triton import (#37)

add flash_attn_triton.py (#34)

Update README.md

Update README.md

Update README.md

Remove print about meta init (#3)

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Add loss function and bool cast

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Create README.md

Upload folder using huggingface_hub

initial commit