vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

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

Browse source 
* 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
This commit is contained in:
slaren 2023-09-28 21:42:38 +02:00 • committed by GitHub
parent 0512d66670
commit 16bc66d947
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
27 changed files with 713 additions and 633 deletions
Download patch file Download diff file Expand all files Collapse all files

12
examples/finetune/finetune.cpp
View file

@ -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);