Skip to content

fix perplexity after c-api refactor by proving a large enough token buffer #389

New issue

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

#

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

Already on GitHub? # to your account

Closed
wants to merge 1 commit into from
Closed

fix perplexity after c-api refactor by proving a large enough token buffer #389

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 6 additions & 1 deletion main.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,12 @@ void perplexity(llama_context * ctx, const gpt_params & params) {
// Download: https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-2-raw-v1.zip?ref=salesforce-research
// Run `./main --perplexity -m models/7B/ggml-model-q4_0.bin -f wiki.test.raw`
// Output: `perplexity: 13.5106 [114/114]`
auto tokens = ::llama_tokenize(ctx, params.prompt.c_str(), true);
std::vector<llama_token> tokens(params.prompt.size()+1); // initialize to prompt numer of chars, since n_tokens <= n_prompt_chars+1
{
const auto res = llama_tokenize(ctx, params.prompt.c_str(), tokens.data(), tokens.size(), true);
assert(res >= 0);
tokens.resize(res);
}

int count = 0;
double nll = 0.0;
Expand Down