CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert : fix conversion for llama 4 (#13567)

Browse Source
This commit is contained in:
Xuan-Son Nguyen
2025-05-15 17:40:07 +02:00
committed by GitHub
parent 02cdd2d8b0
commit c531edfa34
2 changed files with 33 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
convert_hf_to_gguf.py
View File

@@ -2069,6 +2069,9 @@ class Llama4Model(LlamaModel):
self.gguf_writer.add_expert_feed_forward_length(self.hparams["intermediate_size_moe"])
def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None):
if name.startswith("language_model."):
name = name.replace("language_model.", "")
# split the gate_up into gate and up
if "gate_up_proj" in name:
name_up = name.replace("gate_up_proj", "up_proj.weight")