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

Update convert_hf_to_gguf.py 

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Aman Gupta 2026-01-27 23:13:05 +08:00 committed by GitHub
parent d3793348d5
commit d29e8d1eb1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
convert_hf_to_gguf.py
View File

@ -530,7 +530,7 @@ class ModelBase:
up_data = self._up_exp_buffer.pop(bid)
# gate/up shape: (n_expert, n_ff, n_embd), concatenate to (n_expert, n_ff*2, n_embd)
fused_data = torch.cat([gate_data, up_data], dim=1)
fused_name = f"blk.{bid}.ffn_gate_up_exps.weight"
fused_name = self.format_tensor_name(gguf.MODEL_TENSOR.FFN_GATE_UP_EXP, bid)
logger.info(f"Fused gate_exps and up_exps for layer {bid}")
return [(fused_name, fused_data)]
return [] # Wait for up_exps