fix: use model token limit not tokenizer ditto (#5939)
This fixes a token limit bug in the
SentenceTransformersTokenTextSplitter. Before the token limit was taken
from tokenizer used by the model. However, for some models the token
limit of the tokenizer (from `AutoTokenizer.from_pretrained`) does not
equal the token limit of the model. This was a false assumption.
Therefore, the token limit of the text splitter is now taken from the
sentence transformers model token limit.
Twitter: @plasmajens
#### Before submitting
#### Who can review?
@hwchase17 and/or @dev2049
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
