Commit 1ef8c5d68 for llama.cpp
commit 1ef8c5d68495d69b065d28e780264ee01595b6b4
Author: Gabe Goodhart <ghart@us.ibm.com>
Date: Mon Nov 16 15:49:57 2026 -0700
convert : respect max_position_embeddings for granite hybrid (#32436)
* fix(conversion): Respect max_position_embeddings for granite hybrid
Branch: GraniteHybridContextLengthConversion
AI-usage: none
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* style: shorter comment w/ HF reference
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
diff --git a/conversion/granite.py b/conversion/granite.py
index 8bfae2644..66b03ceca 100644
--- a/conversion/granite.py
+++ b/conversion/granite.py
@@ -552,7 +552,9 @@ class GraniteHybridModel(Mamba2Model, GraniteMoeModel):
or not self._ssm_layers
)
self.gguf_writer.add_rope_scaling_finetuned(use_rope)
- if not use_rope:
+ # Set context length to an arbitrary large value if rope is not used AND no previous value is present.
+ # https://huggingface.co/ibm-granite/granite-4.0-h-micro-GGUF/discussions/1
+ if not use_rope and "max_position_embeddings" not in self.hparams:
self.gguf_writer.add_context_length(2**20)
## Validation ##