Open SBrandeis opened 7 months ago
(some comments I had)
GenerationParameters
to TextGenerationParameters
or TextGenerationCommonParameters
(to differentiate from other image generation (and audio, video, etc?))"Bigger changes":
text_generation
and text_to_image
float/integer parameters). Constraints might not be reflected in all generated code but will still be useful to document I was looking into the first added schema and was a bit surprised that they do not match the API schema from inference Endpoints or the Inference API. I thought we wanted to create an external schema that can be used for code generation and other validation to make sure all libraries, API, etc have the same types.
When i looked into it i saw that the main input is called "data" and not "inputs". I also noticed that the "parameters" are "camelCase" and not "snake_case" (in the definitions), Some definitions, e.g. "text-generation" are only for TGI and not for the text-generation
pipeline.
What's the plan here? I don't think we should maintain definitions that need to be adjusted again to work with our products. I thought we start with an API first approach to then integrate into the libraries.
TODO
This issue lists the remaining tasks following #449
sentence-similarity
are emitted by the inference-codegen scriptgenerate
(link)feature-extraction
/text-embedding
taskdepth-estimation
https://github.com/huggingface/transformers/issues/28729 (#472)snake_case
in the JSON Schema to match the current APIs format (#470 )inputs
instead ofdata
in the JSON Schema to match current APIs format (#471 )"Bigger" changes:
feature-extraction
totext-embedding
text-generation
andtext2text-generation