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

lora : add support for non-llama models (#3333)

Browse source 
* lora : add support for non-llama models

ggml-ci

* avoid leaking ggml_context on failure
cleanup

ggml-ci

* lora : allow 1d tensors

* lora : include embd and output layers in size calculation

* fix style
This commit is contained in:
slaren 2023-12-16 18:58:46 +01:00 • committed by GitHub
parent 8a5be3bd58
commit c6c4fc081c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 114 additions and 106 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama.h
View file

@ -39,6 +39,7 @@
#define LLAMA_MAX_RNG_STATE (64*1024)
#define LLAMA_FILE_MAGIC_GGLA 0x67676c61u // 'ggla'
#define LLAMA_FILE_MAGIC_GGSN 0x6767736eu // 'ggsn'
#define LLAMA_SESSION_MAGIC LLAMA_FILE_MAGIC_GGSN