mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 05:48:47 +01:00
speculative : support --color
(#4343)
* speculative: add some colors * minor : add braces --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
parent
5f6e0c0dff
commit
da5eaef1f3
@ -203,8 +203,9 @@ int main(int argc, char ** argv) {
|
|||||||
|
|
||||||
const std::string token_str = llama_token_to_piece(ctx_tgt, id);
|
const std::string token_str = llama_token_to_piece(ctx_tgt, id);
|
||||||
|
|
||||||
printf("%s", token_str.c_str());
|
if (!params.use_color) {
|
||||||
fflush(stdout);
|
printf("%s", token_str.c_str());
|
||||||
|
}
|
||||||
|
|
||||||
if (id == llama_token_eos(model_tgt)) {
|
if (id == llama_token_eos(model_tgt)) {
|
||||||
has_eos = true;
|
has_eos = true;
|
||||||
@ -236,10 +237,18 @@ int main(int argc, char ** argv) {
|
|||||||
++n_past_tgt;
|
++n_past_tgt;
|
||||||
++n_past_dft;
|
++n_past_dft;
|
||||||
++i_dft;
|
++i_dft;
|
||||||
|
if (params.use_color) {
|
||||||
|
// Color token according to its origin sequence
|
||||||
|
printf("\u001b[%dm%s\u001b[37m", (36 - s_keep % 6), token_str.c_str());
|
||||||
|
fflush(stdout);
|
||||||
|
}
|
||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
if (params.use_color) {
|
||||||
|
printf("%s", token_str.c_str());
|
||||||
|
}
|
||||||
|
fflush(stdout);
|
||||||
|
|
||||||
LOG("the sampled target token (%d, '%s') did not match, or we ran out of drafted tokens\n", id, token_str.c_str());
|
LOG("the sampled target token (%d, '%s') did not match, or we ran out of drafted tokens\n", id, token_str.c_str());
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user