Extend the support of T5 models with different encoder-decoder layers #15909
Extend the support of T5 models with different encoder-decoder layers
33163bfb
CISC
commented
on 2025-09-10
Update convert_hf_to_gguf.py
219eadab
Update gguf-py/gguf/constants.py
2161c309
Update gguf-py/gguf/gguf_writer.py
284ceb3d
Update src/llama-arch.cpp
77f0f162
Update src/llama-arch.h
7efe517a
Update src/llama-model.cpp
12a909f1
Update src/llama-model.cpp
634e5a96
Update src/llama-model.cpp
ebef503a
Update src/llama-model.cpp
0acda17a
Update src/llama-hparams.h
19281fe1
Update src/llama-model.cpp
5153072b
Update src/llama-model.cpp
60821df6
Update src/llama-model.cpp
de46320f
Update src/llama-model.cpp
804a982d
Update src/llama-model.cpp
92150875
Update src/llama-model.cpp
11672692
Update src/llama-model.cpp
678aa48a
Update src/llama-model.cpp
d145ee13
Update src/llama-model.cpp
ce90f806
Update src/llama-model.cpp
01002dfb
Update src/llama-model.cpp
3ee2193d
Update src/llama-model.cpp
6cb51f2d
Update src/llama-model.cpp
42f1fdba
Update src/llama-model.cpp
69406502
Rename n_dec_layer --> dec_n_layer
f16d8de5
Adapt to cases when dec_n_layer > n_layer
84e5db4d
CISC
approved these changes
on 2025-09-10
CISC
merged
4f658855
into master 94 days ago
DamonFool
deleted the t5-enhancement branch 94 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub