CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert : proper tensor name mapping for llama4 (#12870)

Browse Source 
* Llama-4 mapping

* remove hacky renaming

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
This commit is contained in:
Xuan-Son Nguyen
2025-04-11 09:23:37 +02:00
committed by GitHub
parent 8b91d5355a
commit 5b1f13cb64
2 changed files with 19 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
convert_hf_to_gguf.py
View File

@@ -1806,10 +1806,6 @@ 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):
name = name.replace("language_model.", "")
name = name.replace("feed_forward.", "mlp.") # a bit hacky for now
name = name.replace(".router.weight", ".gate.weight") # a bit hacky for now
# split the gate_up into gate and up
if "gate_up_proj" in name:
name_up = name.replace("gate_up_proj", "up_proj.weight")