diff options
| author | slaren <slarengh@gmail.com> | 2023-09-28 21:42:38 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-09-28 22:42:38 +0300 |
| commit | 16bc66d9479edd5ee12ec734973554d4493c5dfa (patch) | |
| tree | 4cca787ebd86dd55fd176d27112117c74e9b34c6 /examples/finetune/finetune.cpp | |
| parent | 0512d66670de3f650c579519833c085014b0f200 (diff) | |
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
Diffstat (limited to 'examples/finetune/finetune.cpp')
| -rw-r--r-- | examples/finetune/finetune.cpp | 12 |
1 files changed, 7 insertions, 5 deletions
diff --git a/examples/finetune/finetune.cpp b/examples/finetune/finetune.cpp index 6e29e1c1..b61165fb 100644 --- a/examples/finetune/finetune.cpp +++ b/examples/finetune/finetune.cpp @@ -304,7 +304,7 @@ static void init_model(struct llama_model * input, struct my_llama_model * model gguf_free(mctx); } - hparams.n_vocab = llama_model_n_vocab(input); + hparams.n_vocab = llama_n_vocab(input); hparams.n_ctx = n_ctx; // get tensors from llama_model (possibly mmapped) @@ -1540,12 +1540,14 @@ 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 = false; + struct llama_model_params llama_mparams = llama_model_default_params(); + llama_mparams.vocab_only = false; printf("%s: model base = '%s'\n", __func__, params.fn_model_base); - struct llama_model * lmodel = llama_load_model_from_file(params.fn_model_base, llama_params); - struct llama_context * lctx = llama_new_context_with_model(lmodel, llama_params); + struct llama_model * lmodel = llama_load_model_from_file(params.fn_model_base, llama_mparams); + + struct llama_context_params llama_cparams = llama_context_default_params(); + struct llama_context * lctx = llama_new_context_with_model(lmodel, llama_cparams); struct my_llama_model model; init_model(lmodel, &model, params.fn_model_base, params.common.n_ctx); |