4 Commits
Author SHA1 Message Date
Kartik Gulia 7076180486 model : extend Nemotron MTP support (#29018)
* first fix

* removed unnecessary declarations
2026-09-17 13:52:36 +02:00
Kartik Gulia 7ceed8737f models : allow Nemotron-H models to only define layer_norm_epsilon (#28989)
* allows nemotron models to get by with just defining layer_norm_epsilon

* made changes to load_arch_hparams instead
2026-09-16 15:24:47 +02:00
Kartik GuliaandSigbjørn Skjæret 8c322d5bc4 convert : expand Nemotron H conversion fix (#28689)
* override function for n_h_l

* narrow change for extracting nested attribute

* simpler change; combines has_moe_params

* Apply suggestion from @CISC

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-09-10 13:41:57 +03:00
Kartik Gulia bcb6084a4e convert : fix Nemotron-H LoRA GGUF conversion (#27356)
* convert: fix Nemotron-H LoRA GGUF conversion

* Removed redundant JSON import.
2026-08-27 14:41:24 +02:00