Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-08 05:49:10 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into concedo_experimental

Browse Source 
# Conflicts:
#	Makefile
#	tests/test-tokenizer-0-falcon.py
#	tests/test-tokenizer-0-llama.py
This commit is contained in:
Concedo
2023-11-20 22:37:06 +08:00
parent 4d7c14be73 881800d1f0
commit 56a5fa7a60
21 changed files with 275 additions and 422 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/speculative/speculative.cpp
+15 -2
View File
@@ -96,9 +96,22 @@ int main(int argc, char ** argv) {
}
}
// tokenize the prompt
// Tokenize the prompt
const bool add_bos_tgt = llama_should_add_bos_token(model_tgt);
LOG("add_bos tgt: %d\n", add_bos_tgt);
const bool add_bos_dft = llama_should_add_bos_token(model_dft);
LOG("add_bos dft: %d\n", add_bos_dft);
if (add_bos_tgt != add_bos_dft) {
fprintf(stderr, "%s: error: draft model add_bos must match target model to use speculation but ", __func__);
fprintf(stderr, "add_bos_dft = %d while add_bos_tgt = %d\n", add_bos_dft, add_bos_tgt);
return 1;
}
std::vector<llama_token> inp;
inp = ::llama_tokenize(ctx_tgt, params.prompt, true);
inp = ::llama_tokenize(ctx_tgt, params.prompt, add_bos_tgt, true);
const int max_context_size = llama_n_ctx(ctx_tgt);
const int max_tokens_list_size = max_context_size - 4;