root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 02:14:35 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

Fix issue where interactive mode crashes when input exceeds ctx size (#1789)

Browse Source 
* Fix issue where interactive mode in the main example crashes when input exceeds ctx size

* Ensure the context size is at least 8 tokens in the main example.

Closes #1768
This commit is contained in:
Kerfuffle 2023-06-11 08:19:17 -06:00 committed by GitHub
parent 12b063f0ec
commit fa84c4b3e8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 21 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
examples/common.cpp
View File

@ -632,6 +632,9 @@ void console_set_color(console_state & con_st, console_color_t color) {
case CONSOLE_COLOR_USER_INPUT:
fprintf(con_st.out, ANSI_BOLD ANSI_COLOR_GREEN);
break;
case CONSOLE_COLOR_ERROR:
fprintf(con_st.out, ANSI_BOLD ANSI_COLOR_RED);
break;
}
con_st.color = color;
fflush(con_st.out);

3
examples/common.h
View File

@ -112,7 +112,8 @@ struct llama_context * llama_init_from_gpt_params(const gpt_params & params);
enum console_color_t {
CONSOLE_COLOR_DEFAULT=0,
CONSOLE_COLOR_PROMPT,
CONSOLE_COLOR_USER_INPUT
CONSOLE_COLOR_USER_INPUT,
CONSOLE_COLOR_ERROR
};
struct console_state {

16
examples/main/main.cpp
View File

@ -81,6 +81,9 @@ int main(int argc, char ** argv) {
if (params.n_ctx > 2048) {
fprintf(stderr, "%s: warning: model does not support context sizes greater than 2048 tokens (%d specified);"
"expect poor results\n", __func__, params.n_ctx);
} else if (params.n_ctx < 8) {
fprintf(stderr, "%s: warning: minimum context size is 8, using minimum size.\n", __func__);
params.n_ctx = 8;
}
fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT);
@ -331,6 +334,19 @@ int main(int argc, char ** argv) {
while ((n_remain != 0 && !is_antiprompt) || params.interactive) {
// predict
if (embd.size() > 0) {
// Note: n_ctx - 4 here is to match the logic for commandline prompt handling via
// --prompt or --file which uses the same value.
auto max_embd_size = n_ctx - 4;
// Ensure the input doesn't exceed the context size by truncating embd if necessary.
if ((int)embd.size() > max_embd_size) {
auto skipped_tokens = embd.size() - max_embd_size;
console_set_color(con_st, CONSOLE_COLOR_ERROR);
printf("<<input too long: skipped %ld token%s>>", skipped_tokens, skipped_tokens != 1 ? "s" : "");
console_set_color(con_st, CONSOLE_COLOR_DEFAULT);
fflush(stdout);
embd.resize(max_embd_size);
}
// infinite text generation via context swapping
// if we run out of context:
// - take the n_keep first tokens from the original prompt (via n_past)