diff --git a/common/common.cpp b/common/common.cpp
index e43615f31..d1b92250a 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -819,9 +819,9 @@ std::string fs_get_cache_file(const std::string & filename) {
 //
 // Model utils
 //
-struct common_init_result common_init_from_common_params(common_params & params) {
+struct common_init_result common_init_from_params(common_params & params) {
     common_init_result iparams;
-    auto mparams = common_model_params_from_common_params(params);
+    auto mparams = common_model_params_to_llama(params);
 
     llama_model * model = nullptr;
 
@@ -863,7 +863,7 @@ struct common_init_result common_init_from_common_params(common_params & params)
         }
     }
 
-    auto cparams = common_context_params_from_common_params(params);
+    auto cparams = common_context_params_to_llama(params);
 
     llama_context * lctx = llama_new_context_with_model(model, cparams);
     if (lctx == NULL) {
@@ -970,7 +970,7 @@ void common_lora_adapters_apply(struct llama_context * ctx, std::vector<common_l
     }
 }
 
-struct llama_model_params common_model_params_from_common_params(const common_params & params) {
+struct llama_model_params common_model_params_to_llama(const common_params & params) {
     auto mparams = llama_model_default_params();
 
     if (params.n_gpu_layers != -1) {
@@ -1022,7 +1022,7 @@ static ggml_type kv_cache_type_from_str(const std::string & s) {
     throw std::runtime_error("Invalid cache type: " + s);
 }
 
-struct llama_context_params common_context_params_from_common_params(const common_params & params) {
+struct llama_context_params common_context_params_to_llama(const common_params & params) {
     auto cparams = llama_context_default_params();
 
     cparams.n_ctx             = params.n_ctx;
diff --git a/common/common.h b/common/common.h
index a4c23a466..ea2719e4b 100644
--- a/common/common.h
+++ b/common/common.h
@@ -410,10 +410,10 @@ struct common_init_result {
     std::vector<common_lora_adapter_container> lora_adapters;
 };
 
-struct common_init_result     common_init_from_common_params(common_params & params);
+struct common_init_result     common_init_from_params(common_params & params);
 
-struct llama_model_params     common_model_params_from_common_params  (const common_params & params);
-struct llama_context_params   common_context_params_from_common_params(const common_params & params);
+struct llama_model_params     common_model_params_to_llama  (const common_params & params);
+struct llama_context_params   common_context_params_to_llama(const common_params & params);
 struct ggml_threadpool_params ggml_threadpool_params_from_cpu_params(const cpu_params & params);
 
 struct llama_model * common_load_model_from_url(const char * model_url, const char * path_model, const char * hf_token, const struct llama_model_params & params);
diff --git a/examples/batched-bench/batched-bench.cpp b/examples/batched-bench/batched-bench.cpp
index f62bd5687..81c3220ad 100644
--- a/examples/batched-bench/batched-bench.cpp
+++ b/examples/batched-bench/batched-bench.cpp
@@ -36,7 +36,7 @@ int main(int argc, char ** argv) {
 
     // initialize the model
 
-    llama_model_params model_params = common_model_params_from_common_params(params);
+    llama_model_params model_params = common_model_params_to_llama(params);
 
     llama_model * model = llama_load_model_from_file(params.model.c_str(), model_params);
 
@@ -45,7 +45,7 @@ int main(int argc, char ** argv) {
         return 1;
     }
 
-    llama_context_params ctx_params = common_context_params_from_common_params(params);
+    llama_context_params ctx_params = common_context_params_to_llama(params);
 
     // ensure enough sequences are available
     ctx_params.n_seq_max = n_pl.empty() ? 1 : *std::max_element(n_pl.begin(), n_pl.end());
diff --git a/examples/batched/batched.cpp b/examples/batched/batched.cpp
index abab45f99..3b554033e 100644
--- a/examples/batched/batched.cpp
+++ b/examples/batched/batched.cpp
@@ -39,7 +39,7 @@ int main(int argc, char ** argv) {
 
     // initialize the model
 
-    llama_model_params model_params = common_model_params_from_common_params(params);
+    llama_model_params model_params = common_model_params_to_llama(params);
 
     llama_model * model = llama_load_model_from_file(params.model.c_str(), model_params);
 
@@ -57,7 +57,7 @@ int main(int argc, char ** argv) {
 
     // initialize the context
 
-    llama_context_params ctx_params = common_context_params_from_common_params(params);
+    llama_context_params ctx_params = common_context_params_to_llama(params);
 
     ctx_params.n_ctx   = n_kv_req;
     ctx_params.n_batch = std::max(n_predict, n_parallel);
diff --git a/examples/cvector-generator/cvector-generator.cpp b/examples/cvector-generator/cvector-generator.cpp
index d8ca3f1ad..69e141ecb 100644
--- a/examples/cvector-generator/cvector-generator.cpp
+++ b/examples/cvector-generator/cvector-generator.cpp
@@ -413,7 +413,7 @@ int main(int argc, char ** argv) {
     llama_numa_init(params.numa);
 
     // load the model to get hparams
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     llama_model * model = llama_init.model;
     llama_context * ctx = llama_init.context;
diff --git a/examples/embedding/embedding.cpp b/examples/embedding/embedding.cpp
index 96fd4c664..3f18fc6a7 100644
--- a/examples/embedding/embedding.cpp
+++ b/examples/embedding/embedding.cpp
@@ -95,7 +95,7 @@ int main(int argc, char ** argv) {
     llama_numa_init(params.numa);
 
     // load the model
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     llama_model * model = llama_init.model;
     llama_context * ctx = llama_init.context;
diff --git a/examples/eval-callback/eval-callback.cpp b/examples/eval-callback/eval-callback.cpp
index c24cea67c..fb52db4e1 100644
--- a/examples/eval-callback/eval-callback.cpp
+++ b/examples/eval-callback/eval-callback.cpp
@@ -160,7 +160,7 @@ int main(int argc, char ** argv) {
     params.warmup = false;
 
     // init
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     llama_model * model = llama_init.model;
     llama_context * ctx = llama_init.context;
diff --git a/examples/gritlm/gritlm.cpp b/examples/gritlm/gritlm.cpp
index 96f31436c..6e42fa073 100644
--- a/examples/gritlm/gritlm.cpp
+++ b/examples/gritlm/gritlm.cpp
@@ -160,8 +160,8 @@ int main(int argc, char * argv[]) {
 
     common_init();
 
-    llama_model_params mparams = common_model_params_from_common_params(params);
-    llama_context_params cparams = common_context_params_from_common_params(params);
+    llama_model_params mparams = common_model_params_to_llama(params);
+    llama_context_params cparams = common_context_params_to_llama(params);
 
     llama_backend_init();
 
diff --git a/examples/imatrix/imatrix.cpp b/examples/imatrix/imatrix.cpp
index 659fdded8..a663187a8 100644
--- a/examples/imatrix/imatrix.cpp
+++ b/examples/imatrix/imatrix.cpp
@@ -607,7 +607,7 @@ int main(int argc, char ** argv) {
     params.warmup = false;
 
     // init
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     llama_model * model = llama_init.model;
     llama_context * ctx = llama_init.context;
diff --git a/examples/infill/infill.cpp b/examples/infill/infill.cpp
index a245be88f..cddc034c6 100644
--- a/examples/infill/infill.cpp
+++ b/examples/infill/infill.cpp
@@ -174,7 +174,7 @@ int main(int argc, char ** argv) {
 
     // load the model and apply lora adapter, if any
     LOG_INF("%s: load the model and apply lora adapter, if any\n", __func__);
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     model = llama_init.model;
     ctx = llama_init.context;
diff --git a/examples/llava/llava-cli.cpp b/examples/llava/llava-cli.cpp
index c3b35bc7f..5f9abe2b6 100644
--- a/examples/llava/llava-cli.cpp
+++ b/examples/llava/llava-cli.cpp
@@ -219,7 +219,7 @@ static struct llama_model * llava_init(common_params * params) {
     llama_backend_init();
     llama_numa_init(params->numa);
 
-    llama_model_params model_params = common_model_params_from_common_params(*params);
+    llama_model_params model_params = common_model_params_to_llama(*params);
 
     llama_model * model = llama_load_model_from_file(params->model.c_str(), model_params);
     if (model == NULL) {
@@ -240,7 +240,7 @@ static struct llava_context * llava_init_context(common_params * params, llama_m
     auto ctx_clip = clip_model_load(clip_path, /*verbosity=*/ 1);
 
 
-    llama_context_params ctx_params = common_context_params_from_common_params(*params);
+    llama_context_params ctx_params = common_context_params_to_llama(*params);
     ctx_params.n_ctx           = params->n_ctx < 2048 ? 2048 : params->n_ctx; // we need a longer context size to process image embeddings
 
     llama_context * ctx_llama = llama_new_context_with_model(model, ctx_params);
diff --git a/examples/llava/minicpmv-cli.cpp b/examples/llava/minicpmv-cli.cpp
index 05df2c359..6b666de1b 100644
--- a/examples/llava/minicpmv-cli.cpp
+++ b/examples/llava/minicpmv-cli.cpp
@@ -29,7 +29,7 @@ static struct llama_model * llava_init(common_params * params) {
     llama_backend_init();
     llama_numa_init(params->numa);
 
-    llama_model_params model_params = common_model_params_from_common_params(*params);
+    llama_model_params model_params = common_model_params_to_llama(*params);
 
     llama_model * model = llama_load_model_from_file(params->model.c_str(), model_params);
     if (model == NULL) {
@@ -45,7 +45,7 @@ static struct llava_context * llava_init_context(common_params * params, llama_m
         prompt = "describe the image in detail.";
     }
 
-    llama_context_params ctx_params = common_context_params_from_common_params(*params);
+    llama_context_params ctx_params = common_context_params_to_llama(*params);
     if (params->n_ctx < 2048) {
         // warn user here, "Image processing requires at least 2048 context, setting context to 2048"
         LOG_WRN("%s: Image processing requires at least 2048 context, setting context to 2048\n" , __func__);
diff --git a/examples/lookahead/lookahead.cpp b/examples/lookahead/lookahead.cpp
index c238bcf4b..f9e4aba81 100644
--- a/examples/lookahead/lookahead.cpp
+++ b/examples/lookahead/lookahead.cpp
@@ -56,7 +56,7 @@ int main(int argc, char ** argv) {
     llama_numa_init(params.numa);
 
     // load the target model
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     llama_model * model = llama_init.model;
     llama_context * ctx = llama_init.context;
diff --git a/examples/lookup/lookup-create.cpp b/examples/lookup/lookup-create.cpp
index 2706f6200..7ced0aa97 100644
--- a/examples/lookup/lookup-create.cpp
+++ b/examples/lookup/lookup-create.cpp
@@ -23,7 +23,7 @@ int main(int argc, char ** argv){
     llama_numa_init(params.numa);
 
     // load the model
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     llama_model * model = llama_init.model;
     llama_context * ctx = llama_init.context;
diff --git a/examples/lookup/lookup-stats.cpp b/examples/lookup/lookup-stats.cpp
index 0f4de5510..7faebe7ba 100644
--- a/examples/lookup/lookup-stats.cpp
+++ b/examples/lookup/lookup-stats.cpp
@@ -28,7 +28,7 @@ int main(int argc, char ** argv){
     llama_numa_init(params.numa);
 
     // load the model
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     llama_model * model = llama_init.model;
     llama_context * ctx = llama_init.context;
diff --git a/examples/lookup/lookup.cpp b/examples/lookup/lookup.cpp
index 7950e38be..82fc7d466 100644
--- a/examples/lookup/lookup.cpp
+++ b/examples/lookup/lookup.cpp
@@ -31,7 +31,7 @@ int main(int argc, char ** argv){
     llama_numa_init(params.numa);
 
     // load the model
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     llama_model * model = llama_init.model;
     llama_context * ctx = llama_init.context;
diff --git a/examples/main/main.cpp b/examples/main/main.cpp
index 7ba7ed879..2e70f2c56 100644
--- a/examples/main/main.cpp
+++ b/examples/main/main.cpp
@@ -197,7 +197,7 @@ int main(int argc, char ** argv) {
 
     // load the model and apply lora adapter, if any
     LOG_INF("%s: load the model and apply lora adapter, if any\n", __func__);
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     model = llama_init.model;
     ctx = llama_init.context;
diff --git a/examples/parallel/parallel.cpp b/examples/parallel/parallel.cpp
index 31fbf0945..20274c147 100644
--- a/examples/parallel/parallel.cpp
+++ b/examples/parallel/parallel.cpp
@@ -130,7 +130,7 @@ int main(int argc, char ** argv) {
     llama_numa_init(params.numa);
 
     // load the target model
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     llama_model * model = llama_init.model;
     llama_context * ctx = llama_init.context;
diff --git a/examples/passkey/passkey.cpp b/examples/passkey/passkey.cpp
index 4c919bf29..09bba708f 100644
--- a/examples/passkey/passkey.cpp
+++ b/examples/passkey/passkey.cpp
@@ -61,7 +61,7 @@ int main(int argc, char ** argv) {
 
     // initialize the model
 
-    llama_model_params model_params = common_model_params_from_common_params(params);
+    llama_model_params model_params = common_model_params_to_llama(params);
 
     llama_model * model = llama_load_model_from_file(params.model.c_str(), model_params);
 
@@ -72,7 +72,7 @@ int main(int argc, char ** argv) {
 
     // initialize the context
 
-    llama_context_params ctx_params = common_context_params_from_common_params(params);
+    llama_context_params ctx_params = common_context_params_to_llama(params);
 
     ctx_params.n_ctx = llama_n_ctx_train(model)*n_grp + n_keep;
 
diff --git a/examples/perplexity/perplexity.cpp b/examples/perplexity/perplexity.cpp
index 1fccf1d8f..0f6092031 100644
--- a/examples/perplexity/perplexity.cpp
+++ b/examples/perplexity/perplexity.cpp
@@ -2004,7 +2004,7 @@ int main(int argc, char ** argv) {
     llama_numa_init(params.numa);
 
     // load the model and apply lora adapter, if any
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     llama_model * model = llama_init.model;
     llama_context * ctx = llama_init.context;
diff --git a/examples/retrieval/retrieval.cpp b/examples/retrieval/retrieval.cpp
index 24d05885b..1768aae51 100644
--- a/examples/retrieval/retrieval.cpp
+++ b/examples/retrieval/retrieval.cpp
@@ -149,7 +149,7 @@ int main(int argc, char ** argv) {
     llama_numa_init(params.numa);
 
     // load the model
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     llama_model * model = llama_init.model;
     llama_context * ctx = llama_init.context;
diff --git a/examples/save-load-state/save-load-state.cpp b/examples/save-load-state/save-load-state.cpp
index fd9182451..3866cfa27 100644
--- a/examples/save-load-state/save-load-state.cpp
+++ b/examples/save-load-state/save-load-state.cpp
@@ -28,7 +28,7 @@ int main(int argc, char ** argv) {
     std::string result2;
 
     // init
-    common_init_result llama_init = common_init_from_common_params(params);
+    common_init_result llama_init = common_init_from_params(params);
 
     llama_model * model = llama_init.model;
     llama_context * ctx = llama_init.context;
@@ -92,7 +92,7 @@ int main(int argc, char ** argv) {
     llama_free(ctx);
 
     // make new context
-    auto * ctx2 = llama_new_context_with_model(model, common_context_params_from_common_params(params));
+    auto * ctx2 = llama_new_context_with_model(model, common_context_params_to_llama(params));
 
     llama_sampler * smpl2 = llama_sampler_chain_init(sparams);
 
@@ -152,7 +152,7 @@ int main(int argc, char ** argv) {
     }
 
     // make new context
-    auto * ctx3 = llama_new_context_with_model(model, common_context_params_from_common_params(params));
+    auto * ctx3 = llama_new_context_with_model(model, common_context_params_to_llama(params));
 
     llama_sampler * smpl3 = llama_sampler_chain_init(sparams);
 
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 97b04a2cd..2e1d24189 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -668,7 +668,7 @@ struct server_context {
         // dedicate one sequence to the system prompt
         params.n_parallel += 1;
 
-        common_init_result llama_init = common_init_from_common_params(params);
+        common_init_result llama_init = common_init_from_params(params);
 
         model = llama_init.model;
         ctx   = llama_init.context;
diff --git a/examples/simple/simple.cpp b/examples/simple/simple.cpp
index 0867bf3c6..9c26086fe 100644
--- a/examples/simple/simple.cpp
+++ b/examples/simple/simple.cpp
@@ -33,7 +33,7 @@ int main(int argc, char ** argv) {
 
     // initialize the model
 
-    llama_model_params model_params = common_model_params_from_common_params(params);
+    llama_model_params model_params = common_model_params_to_llama(params);
 
     llama_model * model = llama_load_model_from_file(params.model.c_str(), model_params);
 
@@ -44,7 +44,7 @@ int main(int argc, char ** argv) {
 
     // initialize the context
 
-    llama_context_params ctx_params = common_context_params_from_common_params(params);
+    llama_context_params ctx_params = common_context_params_to_llama(params);
 
     llama_context * ctx = llama_new_context_with_model(model, ctx_params);
 
diff --git a/examples/speculative/speculative.cpp b/examples/speculative/speculative.cpp
index 55d13fc14..5a7b3084f 100644
--- a/examples/speculative/speculative.cpp
+++ b/examples/speculative/speculative.cpp
@@ -66,7 +66,7 @@ int main(int argc, char ** argv) {
     llama_context * ctx_dft = NULL;
 
     // load the target model
-    common_init_result llama_init_tgt = common_init_from_common_params(params);
+    common_init_result llama_init_tgt = common_init_from_params(params);
     model_tgt = llama_init_tgt.model;
     ctx_tgt = llama_init_tgt.context;
 
@@ -78,7 +78,7 @@ int main(int argc, char ** argv) {
     }
 
     params.cpuparams_batch.n_threads = params.draft_cpuparams_batch.n_threads;
-    common_init_result llama_init_dft = common_init_from_common_params(params);
+    common_init_result llama_init_dft = common_init_from_params(params);
     model_dft = llama_init_dft.model;
     ctx_dft = llama_init_dft.context;