Skip to content

convert : move rope_parameters to TextModel class #18061

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ngxson merged 2 commits into from
Dec 15, 2025
Merged

convert : move rope_parameters to TextModel class #18061

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
88b2a66
make sure to search text_config for rope parameters
CISC Dec 15, 2025
dcaf717
move rope_parameters to TextModel class
CISC Dec 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 9 additions & 8 deletions convert_hf_to_gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,19 +136,11 @@ def __init__(self, dir_model: Path, ftype: gguf.LlamaFileType, fname_out: Path,
self.remote_hf_model_id = remote_hf_model_id
self.sentence_transformers_dense_modules = sentence_transformers_dense_modules
self.hparams = ModelBase.load_hparams(self.dir_model, self.is_mistral_format) if hparams is None else hparams
self.rope_parameters = self.hparams.get("rope_parameters", self.hparams.get("rope_scaling")) or {}
self.model_tensors = self.index_tensors(remote_hf_model_id=remote_hf_model_id)
self.metadata_override = metadata_override
self.model_name = model_name
self.dir_model_card = dir_model # overridden in convert_lora_to_gguf.py

# Ensure "rope_theta" and "rope_type" is mirrored in rope_parameters
if "full_attention" not in self.rope_parameters and "sliding_attention" not in self.rope_parameters:
if "rope_theta" not in self.rope_parameters and (rope_theta := self.find_hparam(["rope_theta", "global_rope_theta", "rotary_emb_base"], optional=True)) is not None:
self.rope_parameters["rope_theta"] = rope_theta
if "rope_type" not in self.rope_parameters and (rope_type := self.rope_parameters.get("type")) is not None:
self.rope_parameters["rope_type"] = rope_type

# Apply heuristics to figure out typical tensor encoding based on first layer tensor encoding type
if self.ftype == gguf.LlamaFileType.GUESSED:
# NOTE: can't use field "torch_dtype" in config.json, because some finetunes lie.
Expand Down Expand Up @@ -765,6 +757,15 @@ def __init__(self, *args, **kwargs):
self.block_count = self.find_hparam(["n_layers", "num_hidden_layers", "n_layer", "num_layers"])
self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count)

self.rope_parameters = self.hparams.get("rope_parameters", self.hparams.get("rope_scaling")) or {}

# Ensure "rope_theta" and "rope_type" is mirrored in rope_parameters
if "full_attention" not in self.rope_parameters and "sliding_attention" not in self.rope_parameters:
if "rope_theta" not in self.rope_parameters and (rope_theta := self.find_hparam(["rope_theta", "global_rope_theta", "rotary_emb_base"], optional=True)) is not None:
self.rope_parameters["rope_theta"] = rope_theta
if "rope_type" not in self.rope_parameters and (rope_type := self.rope_parameters.get("type")) is not None:
self.rope_parameters["rope_type"] = rope_type

@classmethod
def __init_subclass__(cls):
# can't use an abstract property, because overriding it without type errors
Expand Down