Comment Comment by RossBencina Some relevant stats from the link:8192 token input sequence length768 embedding dimensions0.27GB model (with 0.07GB model also available)Tokeniser: BertTokenizer [1], 30528 token vocab [2]Is an 8K sequence length directly comparable to text-embedding-ada-002 if the vocabulary is much smaller? I seem to remember its tokeniser has a larger vocabulary.[1] https://huggingface.co/jinaai/jina-embeddings-v2-base-en/blo...[2] https://huggingface.co/jinaai/jina-embeddings-v2-base-en/blo... parent RossBencina 3 years ago
8192 token input sequence length
768 embedding dimensions
0.27GB model (with 0.07GB model also available)
Tokeniser: BertTokenizer [1], 30528 token vocab [2]
Is an 8K sequence length directly comparable to text-embedding-ada-002 if the vocabulary is much smaller? I seem to remember its tokeniser has a larger vocabulary.
[1] https://huggingface.co/jinaai/jina-embeddings-v2-base-en/blo...
[2] https://huggingface.co/jinaai/jina-embeddings-v2-base-en/blo...