tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-18 05:56:00 -04:00
Code Issues Packages Projects Releases Wiki Activity

llama-bench : add model sizes (#2771)

Browse Source 
* llama-bench : add model sizes

* more compact markdown output

* back to GiB

* adjust column sizes
This commit is contained in:
slaren
2023-08-25 15:16:19 +02:00
committed by GitHub
parent 12e2e33a97
commit 154725c543
3 changed files with 74 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
llama.h
View File

@@ -254,7 +254,11 @@ extern "C" {
LLAMA_API int llama_model_n_embd (const struct llama_model * model);
// Get a string describing the model type
LLAMA_API int llama_model_type(const struct llama_model * model, char * buf, size_t buf_size);
LLAMA_API int llama_model_desc(const struct llama_model * model, char * buf, size_t buf_size);
// Returns the total size of all the tensors in the model in bytes
LLAMA_API uint64_t llama_model_size(const struct llama_model * model);
// Returns the total number of parameters in the model
LLAMA_API uint64_t llama_model_n_params(const struct llama_model * model);
// Returns 0 on success
LLAMA_API int llama_model_quantize(