From cfa0750bc9dbc2d957a91b8ed09ab0035d8f3d4e Mon Sep 17 00:00:00 2001 From: ningshanwutuobang Date: Wed, 28 Jun 2023 23:53:37 +0800 Subject: llama : support input embeddings directly (#1910) * add interface for float input * fixed inpL shape and type * add examples of input floats * add test example for embd input * fixed sampling * add free for context * fixed add end condition for generating * add examples for llava.py * add READMD for llava.py * add READMD for llava.py * add example of PandaGPT * refactor the interface and fixed the styles * add cmake build for embd-input * add cmake build for embd-input * Add MiniGPT-4 example * change the order of the args of llama_eval_internal * fix ci error --- .gitignore | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to '.gitignore') diff --git a/.gitignore b/.gitignore index e7bfd52..4fccec3 100644 --- a/.gitignore +++ b/.gitignore @@ -1,5 +1,6 @@ *.o *.a +*.so .DS_Store .build/ .cache/ @@ -39,8 +40,8 @@ models/* /vdot /server /Pipfile +/embd-input-test /libllama.so - build-info.h arm_neon.h compile_commands.json -- cgit v1.2.3