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

llama : support input embeddings directly (#1910)

Browse source 
* 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
This commit is contained in:
ningshanwutuobang 2023-06-28 23:53:37 +08:00 • committed by GitHub
parent 9d23589d63
commit cfa0750bc9
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
16 changed files with 811 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

35
examples/embd-input/embd-input-test.cpp Normal file
View file

@ -0,0 +1,35 @@
#include "embd-input.h"
#include <stdlib.h>
#include <random>
#include <string.h>
int main(int argc, char** argv) {
auto mymodel = create_mymodel(argc, argv);
int N = 10;
int max_tgt_len = 500;
int n_embd = llama_n_embd(mymodel->ctx);
// add random float embd to test evaluation
float * data = new float[N*n_embd];
std::default_random_engine e;
std::uniform_real_distribution<float> u(0,1);
for (int i=0;i<N*n_embd;i++) {
data[i] = u(e);
}
eval_string(mymodel, "user: what is the color of the flag of UN?");
eval_float(mymodel, data, N);
eval_string(mymodel, "assistant:");
eval_string(mymodel, mymodel->params.prompt.c_str());
const char* tmp;
for (int i=0; i<max_tgt_len; i++) {
tmp = sampling(mymodel);
if (strcmp(tmp, "</s>")==0) break;
printf("%s", tmp);
fflush(stdout);
}
printf("\n");
free_mymodel(mymodel);
return 0;
}