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

add llm_build_mm

Browse source
This commit is contained in:
ngxson 2024-07-07 16:01:05 +02:00
parent b88ce0f892
commit f6d090d7de
4 changed files with 221 additions and 278 deletions
Download patch file Download diff file Expand all files Collapse all files

24
include/llama.h
View file

@ -508,19 +508,29 @@ extern "C" {
const char * fname_out,
const llama_model_quantize_params * params);
// Apply a LoRA adapter to a loaded model
// path_base_model is the path to a higher quality model to use as a base for
// the layers modified by the adapter. Can be NULL to use the current loaded model.
// The model needs to be reloaded before applying a new adapter, otherwise the adapter
// will be applied on top of the previous one
// Load a LoRA adapter from file
// The loaded adapter will be associated to the given model, and will be free when the model is deleted
LLAMA_API struct llama_lora_adapter * llama_lora_adapter_init(
struct llama_model * model,
const char * path_lora);
// Add a loaded LoRA adapter to given context
// This will not modify model's weight
LLAMA_API int32_t llama_lora_adapter_set(
struct llama_context * ctx,
const char * path_lora,
struct llama_lora_adapter * adapter,
float scale);
LLAMA_API int32_t llama_lora_adapter_apply(
// Remove a LoRA adapter from given context
// Return -1 if the adapter is not present in the context
LLAMA_API int32_t llama_lora_adapter_remove(
struct llama_context * ctx,
struct llama_lora_adapter * adapter);
// Manually free a LoRA adapter
// Note: loaded adapters will be free when the associated model is deleted
LLAMA_API void llama_lora_adapter_free(struct llama_lora_adapter * adapter);
// Apply a loaded control vector to a llama_context, or if data is NULL, clear
// the currently loaded vector.
// n_embd should be the size of a single layer's control, and data should point