ollama/model/models
Michael Yang af9708c72d
model: handle multiple eos tokens (#10577)
* get eos_token_id from generation_config.json

* refactor

* include both ids and strings in trace

* comments

* remove special case for gemma3 special vocab (#10743)
2025-12-29 06:38:01 -06:00
..
gemma2 model: handle multiple eos tokens (#10577) 2025-12-29 06:38:01 -06:00
gemma3 model: handle multiple eos tokens (#10577) 2025-12-29 06:38:01 -06:00
llama model: handle multiple eos tokens (#10577) 2025-12-29 06:38:01 -06:00
llama4 model: handle multiple eos tokens (#10577) 2025-12-29 06:38:01 -06:00
mistral3 model: handle multiple eos tokens (#10577) 2025-12-29 06:38:01 -06:00
mllama model: handle multiple eos tokens (#10577) 2025-12-29 06:38:01 -06:00
qwen25vl model: handle multiple eos tokens (#10577) 2025-12-29 06:38:01 -06:00
models.go model: add Qwen2.5-VL support (#10385) 2025-12-29 06:37:59 -06:00