Skip to content

Add general name to train #6752

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Apr 19, 2024
Merged

Add general name to train #6752

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ab0dee5
llama : make general.name optional
ggerganov Apr 16, 2024
27d6f84
train: Add 'general.name' to model metadata
teleprint-me Apr 18, 2024
bb25210
Merge branch 'master' into add-general-name-to-train
teleprint-me Apr 18, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions examples/train-text-from-scratch/train-text-from-scratch.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,7 @@ struct my_llama_model {
static const char * LLM_KV_TRAINING_TYPE_TRAIN_MODEL = "train_model";
static const char * LLM_KV_TRAINING_TYPE = "training.type";

static const char * LLM_KV_GENERAL_NAME = "general.name";
static const char * LLM_KV_GENERAL_ARCHITECTURE = "general.architecture";
static const char * LLM_KV_GENERAL_FILE_TYPE = "general.file_type";

Expand Down Expand Up @@ -529,6 +530,7 @@ static void load_llama_model_gguf(struct gguf_context * fctx, struct ggml_contex

static void save_llama_model_gguf(struct gguf_context * fctx, const char * fn_vocab_model, struct my_llama_model * model) {
const char * arch = "llama";

enum llama_ftype ftype = LLAMA_FTYPE_ALL_F32;

std::vector<char> keybuf;
Expand All @@ -540,6 +542,7 @@ static void save_llama_model_gguf(struct gguf_context * fctx, const char * fn_vo

// set arch
gguf_set_val_str(fctx, LLM_KV_GENERAL_ARCHITECTURE, arch);
gguf_set_val_str(fctx, LLM_KV_GENERAL_NAME, arch);
gguf_set_val_u32(fctx, LLM_KV_GENERAL_FILE_TYPE, ftype);

// set hparams
Expand Down