Streamline embeddings from "non-embedding" models

[iamlemec]

The goal here is to get the big embedding models at the top of the MTEB leaderboard working. There are two changes:

• Fix an inconsistency in output counting for u_batches. Now batch.logits is fully ignored for pooled embeddings.
• Add an attention_type to llama_contex_params that allows for causal, non-causal, or unspecified (model default).

With this PR, we can get accurate results (matching HF) from at least the number 2 spot gte-Qwen2-7B-instruct. For instance, with the command:

./llama-embedding -m gte-qwen2-7b-instruct-f16.gguf -p "hello world" -ngl 99 --pooling last --at
tention non-causal -c 512

• [x] I have read the contributing guidelines
• Self-reported review complexity:
  • [X] Low
  • [ ] Medium
  • [ ] High

[iamlemec]

@compilade cool! just rebased to master