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>

1 files changed, 4 insertions, 1 deletions

diff --git a/examples/train-text-from-scratch/train-text-from-scratch.cpp b/examples/train-text-from-scratch/train-text-from-scratch.cpp
index 7ec8595..61c829e 100644
--- a/examples/train-text-from-scratch/train-text-from-scratch.cpp
+++ b/examples/train-text-from-scratch/train-text-from-scratch.cpp
@@ -3054,7 +3054,8 @@ int main(int argc, char ** argv) {
     struct llama_context_params llama_params = llama_context_default_params();
     llama_params.vocab_only = true;
 
-    struct llama_context * lctx = llama_init_from_file(params.fn_vocab_model, llama_params);
+    struct llama_model * lmodel = llama_load_model_from_file(params.fn_vocab_model, llama_params);
+    struct llama_context * lctx = llama_new_context_with_model(lmodel, llama_params);
 
     struct llama_vocab vocab;
     {
@@ -3395,6 +3396,8 @@ int main(int argc, char ** argv) {
     delete[] compute_addr;
     delete[] compute_buf_0;
     delete[] compute_buf_1;
+    llama_free(lctx);
+    llama_free_model(lmodel);
     ggml_free(model.ctx);
 
     return 0;