Commit History
fix: only use token_type id 0 for fast tokenizer
67dd433
monologg
commited on
feat: add fast tokenizer
cb6e01e
monologg
commited on
docs: inference api template
e9af171
monologg
commited on
docs: update readme
9e8a544
monologg
commited on
docs: add readme
2dbb973
monologg
commited on
fix: model_max_length to 512
baa355e
monologg
commited on
fix: model_max_length to 514
41b3d9b
james.ryu
commited on
fix: model_max_length to 514
436ec9c
james.ryu
commited on
fix: several issues
af74d6b
monologg
commited on
feat: Upload model
8b7c38a
monologg
commited on