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

fix perplexity after c-api refactor (#390)

Browse source 
* preallocate a buffer of fitting size for tokenization (utils.cpp)

* don't create a new std::string (especially here, where it's usually large)
This commit is contained in:
Erik Scholz 2023-03-22 17:09:38 +01:00 • committed by GitHub
parent 40ea807a97
commit 56e659a0b2
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
main.cpp
View file

@ -85,7 +85,7 @@ 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);
auto tokens = ::llama_tokenize(ctx, params.prompt, true);
int count = 0;
double nll = 0.0;