ollama/model
Devon Rifkin c87b910232 WIP: stable ordering for tool args
Right now we deserialize tool call definitions' arguments into golang
maps. These purposefully don't have a predictable iteration order,
whereas we want to maintain the order the user originally provided.

Unstable rendering of arguments means that we break the kv cache, which
this change fixes.

There's no way to build this in a fully backwards compatible way when
executing existing templates exactly as they are. We get around this by
rewriting templates dynamically just before they're rendered. This is
fragile, but perhaps the least bad option?
2025-10-07 15:38:58 -07:00
..
imageproc imageproc mllama refactor (#7537) 2024-12-14 19:50:15 -08:00
input batch: use tensors for outputs (#12185) 2025-09-15 14:33:06 -07:00
models Fixed Deepseek2 adding nil tensor error 2025-10-03 14:20:06 -07:00
parsers WIP: stable ordering for tool args 2025-10-07 15:38:58 -07:00
renderers WIP: stable ordering for tool args 2025-10-07 15:38:58 -07:00
testdata gemma2 impl 2025-03-11 14:35:08 -07:00
bytepairencoding.go multi-regexp pretokenizer (#12325) 2025-09-23 13:21:47 -07:00
bytepairencoding_test.go multi-regexp pretokenizer (#12325) 2025-09-23 13:21:47 -07:00
model.go fix: leaf alt name (#12390) 2025-09-23 17:50:53 -07:00
model_test.go fix: leaf alt name (#12390) 2025-09-23 17:50:53 -07:00
sentencepiece.go model: implement bert in ollama engine (#9080) 2025-09-15 15:35:59 -07:00
sentencepiece_test.go model: implement bert in ollama engine (#9080) 2025-09-15 15:35:59 -07:00
textprocessor.go model: handle multiple eos tokens (#10577) 2025-05-16 13:40:23 -07:00
vocabulary.go embedding gemma model (#12181) 2025-09-04 09:09:07 -07:00
vocabulary_test.go model: treat 'user defined' tokens as special tokens (#11077) 2025-06-16 16:03:16 -07:00
wordpiece.go model: implement bert in ollama engine (#9080) 2025-09-15 15:35:59 -07:00
wordpiece_test.go model: implement bert in ollama engine (#9080) 2025-09-15 15:35:59 -07:00