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

2
examples/embedding/embedding.cpp
View file

@ -67,7 +67,7 @@ int main(int argc, char ** argv) {
fprintf(stderr, "%s: prompt: '%s'\n", __func__, params.prompt.c_str());
fprintf(stderr, "%s: number of tokens in prompt = %zu\n", __func__, embd_inp.size());
for (int i = 0; i < (int) embd_inp.size(); i++) {
fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], llama_token_to_str(ctx, embd_inp[i]));
fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], llama_token_to_str(ctx, embd_inp[i]).c_str());
}
fprintf(stderr, "\n");
}