vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/full-rocm.Dockerfile
#	.devops/full.Dockerfile
#	.devops/llama-cli-cuda.Dockerfile
#	.devops/llama-cli-intel.Dockerfile
#	.devops/llama-cli-rocm.Dockerfile
#	.devops/llama-cli-vulkan.Dockerfile
#	.devops/llama-cli.Dockerfile
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-intel.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.devops/llama-server.Dockerfile
#	CMakeLists.txt
#	CONTRIBUTING.md
#	Makefile
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	requirements.txt
#	src/llama.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-07-19 14:23:33 +08:00
commit 24b9616344
61 changed files with 12994 additions and 936 deletions
Download patch file Download diff file Expand all files Collapse all files

10
gpttype_adapter.cpp
View file

@ -1443,16 +1443,12 @@ ModelLoadResult gpttype_load_model(const load_model_inputs inputs, FileFormat in
lora_base_arg = lora_base.c_str();
}
int err = llama_model_apply_lora_from_file(llamamodel,
lora_filename.c_str(),
1.0f,
lora_base_arg,
kcpp_params->n_threads);
if (err != 0)
{
auto adapter = llama_lora_adapter_init(llamamodel, lora_filename.c_str());
if (adapter == nullptr) {
fprintf(stderr, "%s: error: failed to apply lora adapter\n", __func__);
return ModelLoadResult::FAIL;
}
llama_lora_adapter_set(llama_ctx_v4, adapter, 1.0f);
}
if(mmproj_filename != "" && file_format==FileFormat::GGUF_GENERIC)