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

model : add support for talkie-1930-13b (#22596)

Browse Source 
* initial talkie support, coherent

* reorder to follow convention

* absorb inverse rope

* stop folding scalars to improve quantization

* use broadcasting instead of duplication

* style cleanup

* add scaling support to LoraTorchTensor; use that path in conversion

* use layer_out_scale instead of embd_skip_scale
This commit is contained in:
Niklas Sheth
2026-05-26 07:57:38 +03:00
committed by GitHub
parent 1506d39e76
commit c9d98295a3
14 changed files with 263 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/models.h
+13
View File
@@ -186,6 +186,19 @@ struct llama_model_maincoder : public llama_model_base {
};
struct llama_model_talkie : public llama_model_base {
llama_model_talkie(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;
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_deci : public llama_model_base {
llama_model_deci(const struct llama_model_params & params) : llama_model_base(params) {}
void load_arch_hparams(llama_model_loader & ml) override;