diff options
| author | Didzis Gosko <didzis@users.noreply.github.com> | 2023-06-24 11:47:58 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-06-24 11:47:58 +0300 |
| commit | 527b6fba1d237befb324fd846bda7418c0fa394d (patch) | |
| tree | 360b44abac0c9a53739444b8ba9e4ccf903938cd /examples/main/main.cpp | |
| parent | d7b7484f74d486f77feb4c0b7af7e1718ed91651 (diff) | |
llama : make model stateless and context stateful (llama_state) (#1797)
* llama : make model stateless and context stateful
* llama : minor cleanup
* llama : update internal API declaration
* Apply suggestions from code review
fix style
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Missing model memory release
* Fix style
* Add deprecated warning for public API function llama_init_from_file
* Update public API use cases: move away from deprecated llama_init_from_file
* Deprecate public API function llama_apply_lora_from_file
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'examples/main/main.cpp')
| -rw-r--r-- | examples/main/main.cpp | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/examples/main/main.cpp b/examples/main/main.cpp index 941312f..c1e6bf1 100644 --- a/examples/main/main.cpp +++ b/examples/main/main.cpp @@ -107,12 +107,13 @@ int main(int argc, char ** argv) { llama_init_backend(); + llama_model * model; llama_context * ctx; g_ctx = &ctx; // load the model and apply lora adapter, if any - ctx = llama_init_from_gpt_params(params); - if (ctx == NULL) { + std::tie(model, ctx) = llama_init_from_gpt_params(params); + if (model == NULL) { fprintf(stderr, "%s: error: unable to load model\n", __func__); return 1; } @@ -139,6 +140,7 @@ int main(int argc, char ** argv) { llama_print_timings(ctx); llama_free(ctx); + llama_free_model(model); return 0; } @@ -147,6 +149,7 @@ int main(int argc, char ** argv) { if (params.export_cgraph) { llama_eval_export(ctx, "llama.ggml"); llama_free(ctx); + llama_free_model(model); return 0; } @@ -666,6 +669,7 @@ int main(int argc, char ** argv) { llama_print_timings(ctx); llama_free(ctx); + llama_free_model(model); return 0; } |