matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-14 01:37:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

update llama.cpp submodule to 1e6f6554 (#6208)

Browse Source
This commit is contained in:
Jeffrey Morgan
2024-08-06 15:11:45 -04:00
committed by GitHub
parent d4a7216c82
commit e04c7012c2
4 changed files with 25 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
llm/patches/09-lora.diff
View File

@@ -1,40 +1,32 @@
diff --git a/common/common.cpp b/common/common.cpp
index dbb724fb..c26fe6ee 100644
index 2e8374d5..70d0afde 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -2087,14 +2087,27 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
for (unsigned int i = 0; i < params.lora_adapter.size(); ++i) {
const std::string & lora_adapter = std::get<0>(params.lora_adapter[i]);
float lora_scale = std::get<1>(params.lora_adapter[i]);
+
+ // try to load as gguf
auto adapter = llama_lora_adapter_init(model, lora_adapter.c_str());
if (adapter == nullptr) {
- fprintf(stderr, "%s: error: failed to apply lora adapter\n", __func__);
@@ -2110,9 +2110,21 @@ struct llama_init_result llama_init_from_gpt_params(gpt_params & params) {
loaded_la.adapter = llama_lora_adapter_init(model, la.path.c_str());
if (loaded_la.adapter == nullptr) {
fprintf(stderr, "%s: error: failed to apply lora adapter '%s'\n", __func__, la.path.c_str());
- llama_free(lctx);
- llama_free_model(model);
- return std::make_tuple(nullptr, nullptr);
+ fprintf(stderr, "%s: error: failed to apply lora adapter, trying ggla\n", __func__);
- return iparams;
+
+ // if that fails, try loading as ggla for compatibility
+ int err = llama_model_apply_lora_from_file(model,
+ lora_adapter.c_str(),
+ lora_scale,
+ la.path.c_str(),
+ la.scale,
+ nullptr,
+ params.n_threads);
+ if (err != 0) {
+ fprintf(stderr, "%s: error: failed to apply lora adapter\n", __func__);
+ llama_free(lctx);
+ llama_free_model(model);
+ return std::make_tuple(nullptr, nullptr);
+ return iparams;
+ } else {
+ break;
+ }
+ } else {
+ llama_lora_adapter_set(lctx, adapter, lora_scale);
}
- llama_lora_adapter_set(lctx, adapter, lora_scale);
iparams.lora_adapters.push_back(loaded_la); // copy to list of loaded adapters
}
if (params.ignore_eos) {
diff --git a/include/llama.h b/include/llama.h
index 93fd77ca..b0fb37a6 100644
--- a/include/llama.h
@@ -355,4 +347,4 @@ index 80a0dd0f..9d7b0e17 100644
+ return 1;
+ }
+}
\ No newline at end of file
\ No newline at end of file