Manmohan Sharma d49de1575b fix(serve): decode-tail text match for tool markers ... Token-id sequence match failed because BPE has multiple valid tokenizations of the same text, so the greedy encoder output didn't match the model's sampled path. Instead decode gen_ids directly and search for the marker text. Batch-decoding produces complete text even if single-token decodes return empty strings.		2026-04-22 14:48:51 -07:00
..
_model.py	feat: deploy d24 SFT + polished UI redesign with dark mode (#39)	2026-04-16 19:55:16 -04:00
_tokenizer.py	feat: deploy d24 SFT + polished UI redesign with dark mode (#39)	2026-04-16 19:55:16 -04:00
_tools.py	fix(tools): enable Tavily include_answer and fix UI overflow	2026-04-22 14:20:47 -07:00
serve.py	fix(serve): decode-tail text match for tool markers	2026-04-22 14:48:51 -07:00