vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit '017cc5f446' into concedo_experimental

Browse source 
# Conflicts:
#	.github/ISSUE_TEMPLATE/010-bug-compilation.yml
#	.github/ISSUE_TEMPLATE/019-bug-misc.yml
#	CODEOWNERS
#	examples/batched-bench/batched-bench.cpp
#	examples/batched/batched.cpp
#	examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp
#	examples/gritlm/gritlm.cpp
#	examples/llama-bench/llama-bench.cpp
#	examples/passkey/passkey.cpp
#	examples/quantize-stats/quantize-stats.cpp
#	examples/run/run.cpp
#	examples/simple-chat/simple-chat.cpp
#	examples/simple/simple.cpp
#	examples/tokenize/tokenize.cpp
#	ggml/CMakeLists.txt
#	ggml/src/ggml-metal/CMakeLists.txt
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	scripts/sync-ggml.last
#	src/llama.cpp
#	tests/test-autorelease.cpp
#	tests/test-model-load-cancel.cpp
#	tests/test-tokenizer-0.cpp
#	tests/test-tokenizer-1-bpe.cpp
#	tests/test-tokenizer-1-spm.cpp
This commit is contained in:
Concedo 2025-01-08 23:15:21 +08:00
commit dcfa1eca4e
45 changed files with 806 additions and 229 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/main/main.cpp
View file

@ -495,7 +495,7 @@ int main(int argc, char ** argv) {
}
llama_token decoder_start_token_id = llama_model_decoder_start_token(model);
if (decoder_start_token_id == -1) {
if (decoder_start_token_id == LLAMA_TOKEN_NULL) {
decoder_start_token_id = llama_token_bos(model);
}
@ -832,7 +832,7 @@ int main(int argc, char ** argv) {
// if user stop generation mid-way, we must add EOT to finish model's last response
if (need_insert_eot && format_chat) {
llama_token eot = llama_token_eot(model);
embd_inp.push_back(eot == -1 ? llama_token_eos(model) : eot);
embd_inp.push_back(eot == LLAMA_TOKEN_NULL ? llama_token_eos(model) : eot);
need_insert_eot = false;
}