llama.cpp : split llama_context_params into model and context params (#3301)

* llama.cpp : split llama_context_params into model and context params

ggml-ci

* fix metal build

* fix freq_base/scale default to model value

* llama-bench : keep the same model between tests when possible

* move n_threads to llama_context_params, add n_threads_batch

* fix mpi build

* remove kv_size(), cuda scratch fixes

* remove low-vram option

* add n_threads_batch to system info, refactor to get_system_info()

* add documentation about --threads-batch to the READMEs

* llama-bench fix

* main : fix rope freq/scale warning

* llama.cpp : add llama_get_model
common : add llama_tokenize from model

* remove duplicated ctx/model functions

ggml-ci

* cuda : print total VRAM used

1 files changed, 7 insertions, 5 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 d5205aff..a9cf8a38 100644
--- a/examples/train-text-from-scratch/train-text-from-scratch.cpp
+++ b/examples/train-text-from-scratch/train-text-from-scratch.cpp
@@ -976,14 +976,16 @@ int main(int argc, char ** argv) {
     printf("%s: seed: %u\n", __func__, params.common.seed);
     srand(params.common.seed);
 
-    struct llama_context_params llama_params = llama_context_default_params();
-    llama_params.vocab_only = true;
+    struct llama_model_params mparams = llama_model_default_params();
+    mparams.vocab_only = true;
 
-    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_context_params cparams = llama_context_default_params();
+
+    struct llama_model * lmodel = llama_load_model_from_file(params.fn_vocab_model, mparams);
+    struct llama_context * lctx = llama_new_context_with_model(lmodel, cparams);
 
     struct my_llama_model model;
-    model.hparams.n_vocab = llama_n_vocab(lctx);
+    model.hparams.n_vocab = llama_n_vocab(lmodel);
     model.hparams.n_ctx   = params.common.n_ctx;
     model.hparams.n_embd  = params.n_embd;
     model.hparams.n_head  = params.n_head;