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 branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/ISSUE_TEMPLATE/config.yml
#	.gitignore
#	CMakeLists.txt
#	CONTRIBUTING.md
#	Makefile
#	README.md
#	ci/run.sh
#	common/common.h
#	examples/main-cmake-pkg/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	models/ggml-vocab-bert-bge.gguf.inp
#	models/ggml-vocab-bert-bge.gguf.out
#	models/ggml-vocab-deepseek-coder.gguf.inp
#	models/ggml-vocab-deepseek-coder.gguf.out
#	models/ggml-vocab-deepseek-llm.gguf.inp
#	models/ggml-vocab-deepseek-llm.gguf.out
#	models/ggml-vocab-falcon.gguf.inp
#	models/ggml-vocab-falcon.gguf.out
#	models/ggml-vocab-gpt-2.gguf.inp
#	models/ggml-vocab-gpt-2.gguf.out
#	models/ggml-vocab-llama-bpe.gguf.inp
#	models/ggml-vocab-llama-bpe.gguf.out
#	models/ggml-vocab-llama-spm.gguf.inp
#	models/ggml-vocab-llama-spm.gguf.out
#	models/ggml-vocab-mpt.gguf.inp
#	models/ggml-vocab-mpt.gguf.out
#	models/ggml-vocab-phi-3.gguf.inp
#	models/ggml-vocab-phi-3.gguf.out
#	models/ggml-vocab-starcoder.gguf.inp
#	models/ggml-vocab-starcoder.gguf.out
#	requirements.txt
#	requirements/requirements-convert_legacy_llama.txt
#	scripts/check-requirements.sh
#	scripts/pod-llama.sh
#	src/CMakeLists.txt
#	src/llama.cpp
#	tests/test-rope.cpp
This commit is contained in:
Concedo 2024-07-06 00:25:10 +08:00
commit 5b605d03ea
85 changed files with 4095 additions and 941 deletions
Download patch file Download diff file Expand all files Collapse all files

46
examples/main/main.cpp
View file

@ -38,7 +38,8 @@ static gpt_params * g_params;
static std::vector<llama_token> * g_input_tokens;
static std::ostringstream * g_output_ss;
static std::vector<llama_token> * g_output_tokens;
static bool is_interacting = false;
static bool is_interacting = false;
static bool need_insert_eot = false;
static bool file_exists(const std::string & path) {
std::ifstream f(path.c_str());
@ -100,7 +101,8 @@ static void write_logfile(
static void sigint_handler(int signo) {
if (signo == SIGINT) {
if (!is_interacting && g_params->interactive) {
is_interacting = true;
is_interacting = true;
need_insert_eot = true;
} else {
console::cleanup();
printf("\n");
@ -225,7 +227,14 @@ int main(int argc, char ** argv) {
__func__, n_ctx_train, n_ctx);
}
LOG_TEE("%s: chat template example: %s\n", __func__, llama_chat_format_example(model, params.chat_template).c_str());
// print chat template example in conversation mode
if (params.conversation) {
if (params.enable_chat_template) {
LOG_TEE("%s: chat template example: %s\n", __func__, llama_chat_format_example(model, params.chat_template).c_str());
} else {
LOG_TEE("%s: in-suffix/prefix is specified, chat template will be disabled\n", __func__);
}
}
// print system information
{
@ -256,13 +265,15 @@ int main(int argc, char ** argv) {
}
const bool add_bos = llama_should_add_bos_token(model);
GGML_ASSERT(llama_add_eos_token(model) != 1);
if (!llama_model_has_encoder(model)) {
GGML_ASSERT(llama_add_eos_token(model) != 1);
}
LOG("add_bos: %d\n", add_bos);
std::vector<llama_token> embd_inp;
{
auto prompt = (params.conversation && params.enable_chat_template)
auto prompt = (params.conversation && params.enable_chat_template && !params.prompt.empty())
? chat_add_and_format(model, chat_msgs, "system", params.prompt) // format the system prompt in conversation mode
: params.prompt;
if (params.interactive_first || !params.prompt.empty() || session_tokens.empty()) {
@ -518,6 +529,24 @@ int main(int argc, char ** argv) {
exit(1);
}
if (llama_model_has_encoder(model)) {
int enc_input_size = embd_inp.size();
llama_token * enc_input_buf = embd_inp.data();
if (llama_encode(ctx, llama_batch_get_one(enc_input_buf, enc_input_size, 0, 0))) {
LOG_TEE("%s : failed to eval\n", __func__);
return 1;
}
llama_token decoder_start_token_id = llama_model_decoder_start_token(model);
if (decoder_start_token_id == -1) {
decoder_start_token_id = llama_token_bos(model);
}
embd_inp.clear();
embd_inp.push_back(decoder_start_token_id);
}
while ((n_remain != 0 && !is_antiprompt) || params.interactive) {
// predict
if (!embd.empty()) {
@ -886,6 +915,13 @@ int main(int argc, char ** argv) {
LOG("input tokens: %s\n", LOG_TOKENS_TOSTR_PRETTY(ctx, line_inp).c_str());
// 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);
need_insert_eot = false;
}
embd_inp.insert(embd_inp.end(), line_pfx.begin(), line_pfx.end());
embd_inp.insert(embd_inp.end(), line_inp.begin(), line_inp.end());
embd_inp.insert(embd_inp.end(), line_sfx.begin(), line_sfx.end());