root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

speculative : fix prompt tokenization in speculative example (#4025)

Browse Source 
* Support special tokens and not adding BOS to prompt in speculative

* Adapt to new should_add_bos function

* Ensure tgt and dft have same add_bos setting
This commit is contained in:
Branden Butler 2023-11-20 03:50:04 -06:00 committed by GitHub
parent dae06c06e5
commit 40a34fe8d0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 15 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
examples/speculative/speculative.cpp
View File

@ -94,9 +94,22 @@ int main(int argc, char ** argv) {
} }
} }
// tokenize the prompt
// Tokenize the prompt
const bool add_bos_tgt = llama_should_add_bos_token(model_tgt);
LOG("add_bos tgt: %d\n", add_bos_tgt);
const bool add_bos_dft = llama_should_add_bos_token(model_dft);
LOG("add_bos dft: %d\n", add_bos_dft);
if (add_bos_tgt != add_bos_dft) {
fprintf(stderr, "%s: error: draft model add_bos must match target model to use speculation but ", __func__);
fprintf(stderr, "add_bos_dft = %d while add_bos_tgt = %d\n", add_bos_dft, add_bos_tgt);
return 1;
}
std::vector<llama_token> inp; std::vector<llama_token> inp;
inp = ::llama_tokenize(ctx_tgt, params.prompt, true); inp = ::llama_tokenize(ctx_tgt, params.prompt, add_bos_tgt, true);
const int max_context_size = llama_n_ctx(ctx_tgt); const int max_context_size = llama_n_ctx(ctx_tgt);
const int max_tokens_list_size = max_context_size - 4; const int max_tokens_list_size = max_context_size - 4;