summaryrefslogtreecommitdiff
path: root/llama.h
diff options
context:
space:
mode:
authorslaren <slarengh@gmail.com>2023-08-25 15:16:19 +0200
committerGitHub <noreply@github.com>2023-08-25 15:16:19 +0200
commit154725c5436808e5c519685d0279e850596dbe62 (patch)
tree09190086aae7ffa71a2e8089b0a2fc60074b8196 /llama.h
parent12e2e33a977af73e75885eeee91c5575a77f4e5f (diff)
llama-bench : add model sizes (#2771)
* llama-bench : add model sizes * more compact markdown output * back to GiB * adjust column sizes
Diffstat (limited to 'llama.h')
-rw-r--r--llama.h6
1 files changed, 5 insertions, 1 deletions
diff --git a/llama.h b/llama.h
index 2bcf94e0..d4746817 100644
--- a/llama.h
+++ b/llama.h
@@ -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(