millaguie/llama.cpp
1
0 Fork 0
Code Issues Pull Requests Actions 32 Packages Projects Releases Wiki Activity

examples : fix is_first logic for tokenization (#14329)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov authored and GitHub committed 2025-06-22 20:10:07 +03:00
1 parent af3373f1ad
commit f1f5e82df6
2 files changed
+2 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tools/run/run.cpp
+1 -1
View File
@@ -939,7 +939,7 @@ static int apply_chat_template(const struct common_chat_templates * tmpls, Llama
// Function to tokenize the prompt
static int tokenize_prompt(const llama_vocab * vocab, const std::string & prompt,
std::vector<llama_token> & prompt_tokens, const LlamaData & llama_data) {
const bool is_first = llama_memory_seq_pos_max(llama_get_memory(llama_data.context.get()), 0) == 0;
const bool is_first = llama_memory_seq_pos_max(llama_get_memory(llama_data.context.get()), 0) == -1;
const int n_prompt_tokens = -llama_tokenize(vocab, prompt.c_str(), prompt.size(), NULL, 0, is_first, true);
prompt_tokens.resize(n_prompt_tokens);