happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

convert : move rope_parameters to TextModel class (#18061) 

* make sure to search text_config for rope parameters

* move rope_parameters to TextModel class
This commit is contained in:
Sigbjørn Skjæret 2025-12-15 22:03:16 +01:00 committed by GitHub
parent c45f89d551
commit d6a1e18c65
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
convert_hf_to_gguf.py
View File

@ -136,19 +136,11 @@ class ModelBase:
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.
@ -765,6 +757,15 @@ class TextModel(ModelBase):
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