ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Refactor lora adapter support (#8332)

Browse source 
* lora: load to devide buft

* add patch tensor function

* correct tensor patch

* llama_lora_adapter_apply

* correct ggml_backend_tensor_copy

* add llm_build_mm

* fix auto merge

* update based on review comments

* add convert script

* no more transpose A

* add f16 convert

* add metadata check

* add sanity check

* fix ftype

* add requirements

* fix requirements

* fix outfile

* conversion: only allow selected models

* fix types

* cuda : do not use dmmv if the tensor does not have enough cols

* llama : lora fixes

* do not disable mmap with lora

Co-authored-by: slaren <slarengh@gmail.com>

* llm_build_lora_mm_id

* convert_lora : MoE LoRA conversion support

* convert_lora : prefer safetensors, similarly to convert_hf

* convert_hf : simplify modify_tensors for InternLM2

* convert_lora : lazy conversion

* llama : load and use alpha from LoRA adapters

* llama : use llm_build_lora_mm in most model graphs

* auto scale

* Revert "auto scale"

This reverts commit 42415a4874e0f963e4aca6796ea5dfb97cd17464.

* remove redundant params

* Apply suggestions from code review

Co-authored-by: slaren <slarengh@gmail.com>

* change kv metadata

* move add_type to __init__

* convert_hf : move add_type to main()

* convert_lora : use the GGUFWriter from Model instead of overwriting it

---------

Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: Francis Couture-Harpin <git@compilade.net>
This commit is contained in:
Xuan Son Nguyen 2024-07-15 20:50:47 +02:00 • committed by GitHub
parent 4db8f60fe7
commit 97bdd26eee
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 963 additions and 530 deletions
Download patch file Download diff file Expand all files Collapse all files

13
common/common.cpp
View file

@ -685,7 +685,6 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
if (arg == "--lora") {
CHECK_ARG
params.lora_adapter.emplace_back(argv[i], 1.0f);
params.use_mmap = false;
return true;
}
if (arg == "--lora-scaled") {
@ -693,7 +692,6 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
const char* lora_adapter = argv[i];
CHECK_ARG
params.lora_adapter.emplace_back(lora_adapter, std::stof(argv[i]));
params.use_mmap = false;
return true;
}
if (arg == "--lora-base") {
@ -2089,19 +2087,14 @@ 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]);
int err = llama_model_apply_lora_from_file(model,
lora_adapter.c_str(),
lora_scale,
((i > 0) || params.lora_base.empty())
? NULL
: params.lora_base.c_str(),
params.n_threads);
if (err != 0) {
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__);
llama_free(lctx);
llama_free_model(model);
return std::make_tuple(nullptr, nullptr);
}
llama_lora_adapter_set(lctx, adapter, lora_scale);
}
if (params.ignore_eos) {