top | item 46653395 (no title) marquesine | 1 month ago Yes, that's the purpose of TOON.https://github.com/toon-format/toon discuss order hn newest koakuma-chan|1 month ago Is there evidence that LLMs adhere to this format better than to JSON? I doubt that. iLoveOncall|1 month ago It is 100% guaranteed that they DON'T. Toon is 3 months old, it's not used by anyone, and it's therefore not in the training set of any model. TheTaytay|1 month ago Their benchmarks compare it against other formats as input, not as output. load replies (1) prats226|1 month ago Nice, it would be good idea to develop CFG for this as well so can embed it into all these constrained decoding libraries
koakuma-chan|1 month ago Is there evidence that LLMs adhere to this format better than to JSON? I doubt that. iLoveOncall|1 month ago It is 100% guaranteed that they DON'T. Toon is 3 months old, it's not used by anyone, and it's therefore not in the training set of any model. TheTaytay|1 month ago Their benchmarks compare it against other formats as input, not as output. load replies (1)
iLoveOncall|1 month ago It is 100% guaranteed that they DON'T. Toon is 3 months old, it's not used by anyone, and it's therefore not in the training set of any model.
TheTaytay|1 month ago Their benchmarks compare it against other formats as input, not as output. load replies (1)
prats226|1 month ago Nice, it would be good idea to develop CFG for this as well so can embed it into all these constrained decoding libraries
koakuma-chan|1 month ago
iLoveOncall|1 month ago
TheTaytay|1 month ago
prats226|1 month ago