llama : combined beam search + grammar sampling strategy
#2.923 aberto em 31 de ago. de 2023
Métricas do repositório
- Stars
- (124.134 estrelas)
- Métricas de merge de PR
- (Mesclagem média 6d 8h) (389 fundiu PRs em 30d)
Description
This feature was proposed by @spion in https://github.com/ggerganov/llama.cpp/issues/2813#issuecomment-1694390583
In some cases, its useful to do constrained evaluation of logits based on a union of possible text values, then pick the sum { logits } (i.e. product(probabilities)) that gives the most probable outcome overall.
E.g. template (using MS guidance)
{{#select 'armor'}}leather{{or}}chainmail{{or}}plate{{/select}}
To definitely make the best choice, we'd need to calculate the probability of all 3 token sequences. Its easy if all the choices map to a single token, but with multiple tokens we'd need not just parallel generation but parallel logit evaluation of multiple possible paths.
If we go greedy, we might get suboptimal results in cases multiple choices start with the same logit.
It should be possible to implement this by combining the existing beam search and grammar sampling features. See the discussion in the referenced comment for more info