supports jinaai/jina-embeddings-v2-base-code

[wsxiaoys]

I seems to get jina embeddings convert successfully with

python bert_cpp/convert.py jinaai/jina-embeddings-v2-base-code models/jina-f16.gguf

Seems the only change to original bert is ALiBi, as described in https://huggingface.co/jinaai/jina-embeddings-v2-base-code

It'll be nice if we could adapt ggml_alibi into this repo for jina embedding support

[iamlemec]

Yeah, this would be rad. It does seem like it comes down to adding one or two lines with ggml_alibi. The only concern right now is that we're not using a KV cache, so going up to L=8192 is probably going to be infeasible due to memory. But I do plan on adding in KV cache soon. Let me see if I can get it working in the meantime.