Closed Aisuko closed 6 months ago
As we discussed, we should reduce the image size. So, we should remove sentenceTransformer, it's with too much dependencies.
We prefer all-MiniLM-L12-v2 model, small but strong enough.
all-MiniLM-L12-v2
Here are some examples: https://github.com/Aisuko/notebooks/tree/main/nlp/sentence-similarity/computing-embeddings
As we discussed, we will use https://pypi.org/project/kimchima/
As we discussed, we should reduce the image size. So, we should remove sentenceTransformer, it's with too much dependencies.
We prefer
all-MiniLM-L12-v2
model, small but strong enough.Here are some examples: https://github.com/Aisuko/notebooks/tree/main/nlp/sentence-similarity/computing-embeddings