CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-12 10:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

read arch from gguf.MODEL_ARCH

Browse Source
This commit is contained in:
ibrahimkhadraoui
2025-07-07 10:34:46 +04:00
parent 280dd2dcb7
commit c56ec07a9a
1 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
convert_hf_to_gguf.py
View File

@@ -4909,8 +4909,7 @@ class Mamba2Model(TextModel):
# Fail early for models which don't have a block expansion factor of 2
# TODO: does this really matter?
# skip the assertion for FalconH1 Model
architectures = self.hparams.get("architectures")
if architectures is None or architectures[0] != "FalconH1ForCausalLM":
if self.model_arch != gguf.MODEL_ARCH.FALCON_H1:
assert d_inner == 2 * d_model
assert d_inner % head_dim == 0