tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert : experimental support for --mmproj flag (#13023)

Browse Source 
* convert : experimental support for `--mmproj` flag

* fix bad ctrl+f replace

* fix style

* split into subclasses TextModel and VisionModel

* rename Mode --> ModelBase

* small fix

* correct CLIP_VISION arch name (because existing GGUF already use it)

* Apply suggestions from code review

Co-authored-by: compilade <git@compilade.net>

* fix Mistral3Model

* fix typo

Co-authored-by: compilade <git@compilade.net>

---------

Co-authored-by: compilade <git@compilade.net>
This commit is contained in:
Xuan-Son Nguyen
2025-04-20 23:29:36 +02:00
committed by GitHub
parent 6602304814
commit 2016f07bd1
5 changed files with 663 additions and 295 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
convert_lora_to_gguf.py
View File

@ -24,7 +24,7 @@ if 'NO_LOCAL_GGUF' not in os.environ:
import gguf
# reuse model definitions from convert_hf_to_gguf.py
from convert_hf_to_gguf import LazyTorchTensor, Model
from convert_hf_to_gguf import LazyTorchTensor, ModelBase
logger = logging.getLogger("lora-to-gguf")
@ -340,11 +340,11 @@ if __name__ == '__main__':
sys.exit(1)
else:
logger.info(f"Loading base model: {dir_base_model.name}")
hparams = Model.load_hparams(dir_base_model)
hparams = ModelBase.load_hparams(dir_base_model)
with torch.inference_mode():
try:
model_class = Model.from_model_architecture(hparams["architectures"][0])
model_class = ModelBase.from_model_architecture(hparams["architectures"][0])
except NotImplementedError:
logger.error(f"Model {hparams['architectures'][0]} is not supported")
sys.exit(1)