evaluation
#1
by lightningRalf - opened
Hello,
Has there been done any evaluation?
Like this?
https://paperswithcode.com/sota/semantic-textual-similarity-on-sts-benchmark
Thanks in advance.
Hi there. This model is just an ONNX port of https://huggingface.co/sentence-transformers/distilbert-base-nli-stsb-mean-tokens. So, please refer to that model for more information.
hm, just a hint for you, this is displayed on the top of the model card:
â ď¸ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality.```
lightningRalf changed discussion status to closed
lightningRalf changed discussion status to open
Thanks for the heads up. I just converted the most popular sentence-transformers models, so, feel free to select one of the other ones: https://huggingface.co/models?other=transformers.js&sort=downloads
I'm also working on improving the task detection (so that you will be able to filter by "feature extraction" or "sentence similarity").