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, 15 insertions, 1 deletions

diff --git a/tests/test-tokenizer-0.cpp b/tests/test-tokenizer-0.cpp
index ab1538a..20abe71 100644
--- a/tests/test-tokenizer-0.cpp
+++ b/tests/test-tokenizer-0.cpp
@@ -28,6 +28,7 @@ int main(int argc, char **argv) {
 
     fprintf(stderr, "%s : reading vocab from: '%s'\n", __func__, fname.c_str());
 
+    llama_model * model;
     llama_context * ctx;
 
     // load the vocab
@@ -36,10 +37,18 @@ int main(int argc, char **argv) {
 
         lparams.vocab_only = true;
 
-        ctx = llama_init_from_file(fname.c_str(), lparams);
+        model = llama_load_model_from_file(fname.c_str(), lparams);
+
+        if (model == NULL) {
+            fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
+            return 1;
+        }
+
+        ctx = llama_new_context_with_model(model, lparams);
 
         if (ctx == NULL) {
             fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
+            llama_free_model(model);
             return 1;
         }
     }
@@ -48,6 +57,8 @@ int main(int argc, char **argv) {
 
     if (n_vocab != 32000) {
         fprintf(stderr, "%s : expected 32000 tokens, got %d\n", __func__, n_vocab);
+        llama_free_model(model);
+        llama_free(ctx);
         return 2;
     }
 
@@ -77,10 +88,13 @@ int main(int argc, char **argv) {
             }
             fprintf(stderr, "\n");
 
+            llama_free_model(model);
+            llama_free(ctx);
             return 3;
         }
     }
 
+    llama_free_model(model);
     llama_free(ctx);
 
     return 0;