Small fixes to InferenceEndpointModel #112
Added implementation for missing properties in InferenceEndpointModel
a7e37685
Added tokenized context in greedy generate + handled stop_sequence of…
b1c16da3
Santized endpoint model name
12f73081
Redid disable_tqdm & fixed call to batch generate with logits
11ced4c7
Removed debug flag
a5e8915e
Swapped debug to true
df59c51f
Fixed format changes
41934ce4
Added get original order for InferenceEndpoint calls
69252920
Added option to specify model info in args
a9c2e79a
Merge remote-tracking branch 'huggingface/main' into fix-greedy-gener…
d155217b
Removed model info
d3d2097e
Added model dtype to inference endpoint model config
75614c5d
Fixed format
469efeb3
Revert "Fixed format"
2d3e4e8d
Revert "Added model dtype to inference endpoint model config"
f78fd1b2
Removed cleanup when reusing
f1ec55d9
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub