CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix coloring of last n_batch of prompt, and refactor line input (#221)

Browse Source 
* fix coloring of last `n_batch` of prompt, and refactor line input
* forgot the newline that needs to be sent to the model
* (per #283) try to force flush of color reset in SIGINT handler
This commit is contained in:
Rickey Bowers Jr
2023-03-19 13:44:30 -06:00
committed by GitHub
parent 24568371ae
commit 5c19c70ba6
1 changed files with 24 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
main.cpp
View File

@@ -7,6 +7,7 @@
#include <cstdio> #include <cstdio>
#include <cstring> #include <cstring>
#include <fstream> #include <fstream>
#include <iostream>
#include <map> #include <map>
#include <string> #include <string>
#include <vector> #include <vector>
@@ -997,11 +998,6 @@ int main(int argc, char ** argv) {
break; break;
} }
} }
// reset color to default if we there is no pending user input
if (!input_noecho && params.use_color && (int) embd_inp.size() == input_consumed) {
printf(ANSI_COLOR_RESET);
}
} }
// display text // display text
@@ -1011,6 +1007,10 @@ int main(int argc, char ** argv) {
} }
fflush(stdout); fflush(stdout);
} }
// reset color to default if we there is no pending user input
if (!input_noecho && params.use_color && (int)embd_inp.size() == input_consumed) {
printf(ANSI_COLOR_RESET);
}
// in interactive mode, and not currently processing queued inputs; // in interactive mode, and not currently processing queued inputs;
// check if we should prompt the user for more // check if we should prompt the user for more
@@ -1032,43 +1032,33 @@ int main(int argc, char ** argv) {
} }
// currently being interactive // currently being interactive
if (params.use_color) printf(ANSI_BOLD ANSI_COLOR_GREEN);
std::string buffer;
std::string line;
bool another_line = true; bool another_line = true;
while (another_line) { do {
fflush(stdout); std::getline(std::cin, line);
char buf[256] = {0}; if (line.empty() || line.back() != '\\') {
int n_read;
if (params.use_color) printf(ANSI_BOLD ANSI_COLOR_GREEN);
if (scanf("%255[^\n]%n%*c", buf, &n_read) <= 0) {
// presumable empty line, consume the newline
std::ignore = scanf("%*c");
n_read=0;
}
if (params.use_color) printf(ANSI_COLOR_RESET);
if (n_read > 0 && buf[n_read-1]=='\\') {
another_line = true;
buf[n_read-1] = '\n';
buf[n_read] = 0;
} else {
another_line = false; another_line = false;
buf[n_read] = '\n'; } else {
buf[n_read+1] = 0; line.pop_back(); // Remove the continue character
} }
buffer += line + '\n'; // Append the line to the result
} while (another_line);
if (params.use_color) printf(ANSI_COLOR_RESET);
std::vector<gpt_vocab::id> line_inp = ::llama_tokenize(vocab, buf, false); std::vector<gpt_vocab::id> line_inp = ::llama_tokenize(vocab, buffer, false);
embd_inp.insert(embd_inp.end(), line_inp.begin(), line_inp.end()); embd_inp.insert(embd_inp.end(), line_inp.begin(), line_inp.end());
if (params.instruct) { if (params.instruct) {
embd_inp.insert(embd_inp.end(), inp_sfx.begin(), inp_sfx.end()); embd_inp.insert(embd_inp.end(), inp_sfx.begin(), inp_sfx.end());
}
remaining_tokens -= line_inp.size();
input_noecho = true; // do not echo this again
} }
is_interacting = false; remaining_tokens -= line_inp.size();
input_noecho = true; // do not echo this again
} }
is_interacting = false;
} }
// end of text token // end of text token