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

Find metadata key by enum

Browse source
This commit is contained in:
z5269887 2024-04-11 21:25:06 +08:00
parent 502d069b14
commit 29ed5d60e1
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama.cpp
View file

@ -13515,9 +13515,9 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
gguf_set_val_u32(ctx_out, "general.quantization_version", GGML_QNT_VERSION);
gguf_set_val_u32(ctx_out, "general.file_type", ftype);
// Remove split metadata
gguf_remove_key(ctx_out, "split.no");
gguf_remove_key(ctx_out, "split.count");
gguf_remove_key(ctx_out, "split.tensors.count");
gguf_remove_key(ctx_out, ml.llm_kv(LLM_KV_SPLIT_NO).c_str());
gguf_remove_key(ctx_out, ml.llm_kv(LLM_KV_SPLIT_COUNT).c_str());
gguf_remove_key(ctx_out, ml.llm_kv(LLM_KV_SPLIT_TENSORS_COUNT).c_str());
if (params->kv_overrides) {
const std::vector<llama_model_kv_override> & overrides = *(const std::vector<llama_model_kv_override> *)params->kv_overrides;