Commit History
Update README.md
2a8bd4e
verified
Update detail about Triton Flash Attention with ALiBi implementation
8a9076d
Change attention_probs_dropout_prob to 0.1 so that FlashAttention/triton dependencies are avoided
ed2a544
Update README.md
3970aa9
Update README
785d4c8
Update README.md
ce11e47
Update README.md
fdbb682
Update README.md
7b2f449
update hyperlinks to mosaicml/examples
69ac42c
Update README.md
64bd935
Update README.md
fcc434c
Update README.md
ba7abb1
Update README.md
68a6d88
expand usage instructions in README (#2)
4f0fd4f
Update README.md (#1)
8289db4
Update README.md
ade534e
Update README.md
f4619c8
Update README.md
1dc825e
Update README.md
c8eb665
Update README.md
65996c1
Update README.md
4695bbf
Update README.md
2885f1f
Update README.md
c66f045
Update README.md
c721a25
Update README.md
29c1999
Create README.md
24512df
Upload BertForMaskedLM
1c2f266
initial commit
7de0efa
Daniel King
commited on