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

6
llama.cpp
View file

@ -7032,19 +7032,21 @@ llama_token llama_token_nl(const struct llama_context * ctx) {
int llama_tokenize(
struct llama_context * ctx,
const char * text,
int text_len,
llama_token * tokens,
int n_max_tokens,
bool add_bos) {
return llama_tokenize_with_model(&ctx->model, text, tokens, n_max_tokens, add_bos);
return llama_tokenize_with_model(&ctx->model, text, text_len, tokens, n_max_tokens, add_bos);
}
int llama_tokenize_with_model(
const struct llama_model * model,
const char * text,
int text_len,
llama_token * tokens,
int n_max_tokens,
bool add_bos) {
auto res = llama_tokenize_internal(model->vocab, text, add_bos);
auto res = llama_tokenize_internal(model->vocab, std::string(text, text_len), add_bos);
if (n_max_tokens < (int) res.size()) {
// LLAMA_LOG_ERROR("%s: too many tokens\n", __func__);