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

llama : tokenizer fixes (#2549)

Browse source 
* Merge tokenizer fixes into the gguf branch.

* Add test vocabularies
This commit is contained in:
goerch 2023-08-14 18:30:28 +02:00 • committed by GitHub
parent 8af3a99ff1
commit ec1b100720
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
17 changed files with 612 additions and 147 deletions
Download patch file Download diff file Expand all files Collapse all files

9
examples/save-load-state/save-load-state.cpp
View file

@ -45,9 +45,8 @@ int main(int argc, char ** argv) {
llama_free_model(model);
return 1;
}
auto tokens = std::vector<llama_token>(params.n_ctx);
auto n_prompt_tokens = llama_tokenize(ctx, params.prompt.c_str(), tokens.data(), int(tokens.size()), true);
auto tokens = llama_tokenize(ctx, params.prompt.c_str(), true);
auto n_prompt_tokens = tokens.size();
if (n_prompt_tokens < 1) {
fprintf(stderr, "%s : failed to tokenize prompt\n", __func__);
llama_free(ctx);
@ -92,7 +91,7 @@ int main(int argc, char ** argv) {
auto next_token_str = llama_token_to_str(ctx, next_token);
last_n_tokens_data.push_back(next_token);
printf("%s", next_token_str);
printf("%s", next_token_str.c_str());
if (llama_eval(ctx, &next_token, 1, n_past, params.n_threads)) {
fprintf(stderr, "\n%s : failed to evaluate\n", __func__);
llama_free(ctx);
@ -152,7 +151,7 @@ int main(int argc, char ** argv) {
auto next_token_str = llama_token_to_str(ctx2, next_token);
last_n_tokens_data.push_back(next_token);
printf("%s", next_token_str);
printf("%s", next_token_str.c_str());
if (llama_eval(ctx2, &next_token, 1, n_past, params.n_threads)) {
fprintf(stderr, "\n%s : failed to evaluate\n", __func__);
llama_free(ctx2);