]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model : add AfmoeForCausalLM support (#16477)
authorBartowski <redacted>
Fri, 14 Nov 2025 12:54:10 +0000 (07:54 -0500)
committerGitHub <redacted>
Fri, 14 Nov 2025 12:54:10 +0000 (13:54 +0100)
commite1fcf8b09b8115156313c61bdd42186a7c7fb7be
tree54a3ffd421e6f3b0a11822df5e894f2f80e15813
parent6cd0cf72ce96393f06bd271731e7a8bebeb481c0
model : add AfmoeForCausalLM support (#16477)

* Add AFMOE model support

* Update to vocab

* Add model sizing

* Undo Rope change for ARCEE model

* Address review comments

* Update modeling code is_sliding -> use_rope, replace hard-coded logic

* Fix AFMOE tokenizer

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <redacted>
* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <redacted>
* Update AFMoE tokenizer class identification to be more unique

---------

Co-authored-by: Sigbjørn Skjæret <redacted>
14 files changed:
convert_hf_to_gguf.py
convert_hf_to_gguf_update.py
gguf-py/gguf/constants.py
gguf-py/gguf/tensor_mapping.py
src/CMakeLists.txt
src/llama-arch.cpp
src/llama-arch.h
src/llama-model.cpp
src/llama-model.h
src/llama-vocab.cpp
src/llama-vocab.h
src/models/afmoe.cpp [new file with mode: 0644]
src/models/models.h
src/unicode.cpp