Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

llava : fix tokenization to not add bos after system prompt #3645

Merged
merged 2 commits into from
Oct 16, 2023
Merged

llava : fix tokenization to not add bos after system prompt #3645

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e0fb74c
llava : fix tokenization to not add bos after system prompt
ggerganov Oct 16, 2023
20131fe
set seed
monatis Oct 16, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions examples/llava/llava-utils.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,9 +49,9 @@ inline bool eval_id(struct llama_context * ctx_llama, int id, int * n_past) {
return eval_tokens(ctx_llama, tokens, 1, n_past);
}

inline bool eval_string(struct llama_context * ctx_llama, const char* str, int n_batch, int * n_past){
inline bool eval_string(struct llama_context * ctx_llama, const char* str, int n_batch, int * n_past, bool add_bos){
std::string str2 = str;
std::vector<llama_token> embd_inp = ::llama_tokenize(ctx_llama, str2, true);
std::vector<llama_token> embd_inp = ::llama_tokenize(ctx_llama, str2, add_bos);
eval_tokens(ctx_llama, embd_inp, n_batch, n_past);
return true;
}
Expand Down
12 changes: 7 additions & 5 deletions examples/llava/llava.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,6 +97,7 @@ int main(int argc, char ** argv) {
ctx_params.n_ctx = params.n_ctx < 2048 ? 2048 : params.n_ctx; // we need a longer context size to process image embeddings
ctx_params.n_threads = params.n_threads;
ctx_params.n_threads_batch = params.n_threads_batch == -1 ? params.n_threads : params.n_threads_batch;
ctx_params.seed = params.seed;

llama_context * ctx_llama = llama_new_context_with_model(model, ctx_params);

Expand All @@ -106,7 +107,8 @@ int main(int argc, char ** argv) {
}

// make sure that the correct mmproj was used, i.e., compare apples to apples
int n_llama_embd = llama_n_embd(llama_get_model(ctx_llama));
const int n_llama_embd = llama_n_embd(llama_get_model(ctx_llama));

if (n_img_embd != n_llama_embd) {
printf("%s: embedding dim of the multimodal projector (%d) is not equal to that of LLaMA (%d). Make sure that you use the correct mmproj file.\n", __func__, n_img_embd, n_llama_embd);

Expand All @@ -125,14 +127,14 @@ int main(int argc, char ** argv) {

const int max_tgt_len = params.n_predict < 0 ? 256 : params.n_predict;

// GG: are we sure that the should be a trailing whitespace at the end of this string?
eval_string(ctx_llama, "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\nUSER: ", params.n_batch, &n_past);
eval_string(ctx_llama, "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\nUSER:", params.n_batch, &n_past, true);
eval_image_embd(ctx_llama, image_embd, n_img_pos, params.n_batch, &n_past);
eval_string(ctx_llama, params.prompt.c_str(), params.n_batch, &n_past);
eval_string(ctx_llama, "\nASSISTANT:", params.n_batch, &n_past);
eval_string(ctx_llama, (params.prompt + "\nASSISTANT:").c_str(), params.n_batch, &n_past, false);

// generate the response

printf("\n");
printf("prompt: '%s'\n", params.prompt.c_str());
printf("\n");

for (int i = 0; i < max_tgt_len; i++) {
Expand Down