Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

model: add Mellum architecture (#23966)

Browse Source 
* model: support for Mellum architecture

* model: improve mellum.py formatting

* model: improve mellum.py formatting once again

* deps: downgrade transformers to 4.57.6 (to fix CI)

* deps: remove huggingface_hub dependency

* deps: remove huggingface_hub from test requirements

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Mikhail Podvitskii
2026-06-02 22:11:12 +03:00
committed by GitHub
co-authored by Sigbjørn Skjæret
parent bfb4308b05
commit 4fb16eccce
20 changed files with 344 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/models.h
+12
View File
@@ -411,6 +411,18 @@ struct llama_model_stablelm : public llama_model_base {
std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
};
struct llama_model_mellum : public llama_model_base {
llama_model_mellum(const struct llama_model_params & params) : llama_model_base(params) {}
void load_arch_hparams(llama_model_loader & ml) override;
void load_arch_tensors(llama_model_loader & ml) override;
template <bool iswa>
struct graph : public llm_graph_context {
graph(const llama_model & model, const llm_graph_params & params);
};
std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
};
struct llama_model_qwen : public llama_model_base {
llama_model_qwen(const struct llama_model_params & params) : llama_model_base(params) {}