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

model: Add support for Nanbeige4.2 (#25994)

Browse Source 
* support nanbeige4.2 model

* fix

* fix flake8 Lint check

* fix loop bound check and drop redundant head_dim

---------

Co-authored-by: root <lizongqiang@kanzhun.com>
This commit is contained in:
zql
2026-07-27 17:04:18 +02:00
committed by GitHub
co-authored by root
parent 0324696b8e
commit b77d646751
10 changed files with 265 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/models.h
+16
View File
@@ -424,6 +424,22 @@ struct llama_model_mellum : public llama_model_base {
std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
};
struct llama_model_nanbeige : public llama_model_base {
llama_model_nanbeige(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;
int n_loops = 1;
int n_layer_phys = 0;
bool skip_loop_final_norm = false;
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) {}
void load_arch_hparams(llama_model_loader & ml) override;