train : add general name (ggerganov#6752)

* llama : make general.name optional * train: Add 'general.name' to model metadata Signed-off-by: teleprint-me <[email protected]> --------- Signed-off-by: teleprint-me <[email protected]> Co-authored-by: Georgi Gerganov <[email protected]>
CISC · Apr 19, 2024 · 8b1b1f4 · 8b1b1f4
1 parent bca40e9
commit 8b1b1f4
Showing 1 changed file with 3 additions and 0 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
@@ -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";
 
@@ -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;
@@ -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