]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model : add KORMo model (#18032)
authorHelloKS <redacted>
Mon, 15 Dec 2025 17:51:43 +0000 (02:51 +0900)
committerGitHub <redacted>
Mon, 15 Dec 2025 17:51:43 +0000 (18:51 +0100)
commit9d52f17ae33e8df958e20f3f1b13bfec53ab5a1d
treecdd074d7f23c3a952afeaea66fbf0d8dd063bd8b
parent4529c660c89a8675686cbe2bd1839e85f223f3fc
model : add KORMo model (#18032)

* vocab: add KORMo Tokenizer

* model: add KORMoForCausalLM

* vocab: change pretokenizer to qwen2

* lint: fix unintended line removal

* model: make qwen2 bias tensor optional

* model: use qwen2 architecture for KORMo
convert_hf_to_gguf.py
convert_hf_to_gguf_update.py
gguf-py/gguf/tensor_mapping.py
src/llama-model.cpp
src/llama-vocab.cpp
src/models/qwen2.cpp