mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
convert : force setting sliding_window from original config (#15867)
* convert : force setting sliding_window from original config
This commit modifies the set_gguf_parameters method for EmbeddingGemma
so that it reads the sliding_window parameter from the original model
config.json and uses that value.
The motivation for this change is that the Gemma3TextConfig
constructor adjusts the sliding_window value, which can lead to
inconsistencies when converting models as we expects this value to
match the original model's configuration.
Refs: bb45d3631e/src/transformers/models/gemma3/configuration_gemma3.py (L230)
* fix flake8 error
* add link to huggingface PR
This commit is contained in:
@@ -5128,6 +5128,20 @@ class EmbeddingGemma(Gemma3Model):
|
||||
|
||||
def set_gguf_parameters(self):
|
||||
super().set_gguf_parameters()
|
||||
|
||||
# Override the sliding window size as it gets adjusted by the Gemma3TextConfig
|
||||
# constructor. We want to use the value from the original model's config.json.
|
||||
# ref: https://github.com/huggingface/transformers/pull/40700
|
||||
with open(self.dir_model / "config.json", "r", encoding="utf-8") as f:
|
||||
config = json.load(f)
|
||||
orig_sliding_window = config.get("sliding_window")
|
||||
if orig_sliding_window is None:
|
||||
raise ValueError("sliding_window not found in model config - this is required for the model")
|
||||
|
||||
logger.info(f"Using original sliding_window from config: {orig_sliding_window} "
|
||||
f"instead of {self.hparams['sliding_window']}")
|
||||
self.gguf_writer.add_sliding_window(orig_sliding_window)
|
||||
|
||||
self._try_set_pooling_type()
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user