# Why can't I find a better model?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhy-cant-i-find-a-better-model%2F83740%3E%5C
**Category:** Models\
**Created:** [April 25, 2024, 3:25pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhy-cant-i-find-a-better-model%2F83740 "2024-04-25T15:25:57Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![MMPierre](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/mmpierre/32/26222_2.png) [@MMPierre](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMMPierre)%5C
**Post date:** [April 25, 2024, 3:25pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhy-cant-i-find-a-better-model%2F83740%2F1 "2024-04-25T15:25:57Z")

</div>

I regularly use vector embeddings in my work, especially for sentence similarity tasks (vector search using cosine) and classification tasks (logistic regression/ NN on embeddings). When I started two years ago, the best model I found was ‘Sahajtomar/french\_semantic’ that barely has a 100 downloads.

Every 6 months i check the new SOTA models for sentence similarity and they always perform significantly worse than this one. I am doing something wrong ? I am using every model “out of the box” and I have a neutral benchmark to test my use cases.

It seems weird that i haven’t found a model that perform at least on a similar level …

---

<div class="post-metadata">

**Author:** ![vivek9840](https://avatars.discourse-cdn.com/v4/letter/v/eb8c5e/32.png) [@vivek9840](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fvivek9840)%5C
**Post date:** [April 25, 2024, 5:40pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhy-cant-i-find-a-better-model%2F83740%2F2 "2024-04-25T17:40:24Z")

</div>

I think the reason could be that there are fewer models trained for the French language.