LLM inference in C/C++
C++ ggml
convert : add text_config as fallback [transformers 5.18] (#30040)
Kartik Gulia6c73b3e12dc5
diff --git a/conversion/nemotron.py b/conversion/nemotron.pyindex c9bb3031f4..f7eefcf8d0 100644--- a/conversion/nemotron.py+++ b/conversion/nemotron.py@@ -216,7 +216,7 @@ class NemotronHModel(GraniteHybridModel):hparams = kwargs.pop("hparams", None)if hparams is None:hparams = ModelBase.load_hparams(args[0], self.is_mistral_format)- llm_config = {**hparams, **(hparams.get("llm_config") or {})}+ llm_config = {**hparams, **hparams.get("text_config", {})}has_moe_params = "num_experts_per_tok" in llm_configlayers_block_type = llm_config.get("layers_block_type")