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

Fixing the last deviations from sentencepiece indicated by test-tokenizer-1 (#3170)

Browse source 
* Fix für #2721

* Reenable tokenizer test for LLaMa

* Add `console.cpp` dependency

* Fix dependency to `common`

* Fixing wrong fix.

* Make console usage platform specific

Work on compiler warnings.

* Adapting makefile

* Remove trailing whitespace

* Adapting the other parts of the makefile

* Fix typo.

* Fixing the last deviations from sentencepiece indicated by test-tokenizer-1

* Simplify logic

* Add missing change...

* Fix ugly compiler warning

* llama_tokenize should accept strings containing NUL now

* Adding huichen's test case
This commit is contained in:
goerch 2023-09-16 13:41:33 +02:00 • committed by GitHub
parent e6616cf0db
commit b08e75baea
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 17 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.cpp
View file

@ -801,10 +801,10 @@ std::vector<llama_token> llama_tokenize(
// upper limit for the number of tokens
int n_tokens = text.length() + add_bos;
std::vector<llama_token> result(n_tokens);
n_tokens = llama_tokenize(ctx, text.c_str(), result.data(), result.size(), add_bos);
n_tokens = llama_tokenize(ctx, text.data(), text.length(), result.data(), result.size(), add_bos);
if (n_tokens < 0) {
result.resize(-n_tokens);
int check = llama_tokenize(ctx, text.c_str(), result.data(), result.size(), add_bos);
int check = llama_tokenize(ctx, text.data(), text.length(), result.data(), result.size(), add_bos);
GGML_ASSERT(check == -n_tokens);
} else {
result.resize(n_tokens);