vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

updated tokenizer, added support for scratch buffers for neox and gpt2

Browse source
This commit is contained in:
Concedo 2023-06-19 21:29:06 +08:00
parent cb6daa3171
commit 8e2dc19dc6
5 changed files with 115 additions and 75 deletions
Download patch file Download diff file Expand all files Collapse all files

8
gpttype_adapter.cpp
View file

@ -387,9 +387,15 @@ ModelLoadResult gpttype_load_model(const load_model_inputs inputs, FileFormat in
{
printf("\nAttempting to apply LORA adapter: %s\n", lora_filename.c_str());
const char * lora_base_arg = NULL;
if (lora_base != "") {
printf("Using LORA base model: %s\n", lora_base.c_str());
lora_base_arg = lora_base.c_str();
}
int err = llama_apply_lora_from_file(llama_ctx_v3,
lora_filename.c_str(),
NULL,
lora_base_arg,
n_threads);
if (err != 0)
{