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/workflows/build.yml
#	README.md
#	examples/CMakeLists.txt
#	examples/batched/batched.cpp
#	examples/gritlm/gritlm.cpp
#	examples/llama.android/llama/build.gradle.kts
#	examples/main/README.md
#	examples/retrieval/retrieval.cpp
#	examples/server/CMakeLists.txt
#	examples/server/README.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml.c
#	scripts/compare-commits.sh
#	scripts/sync-ggml.last
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tests/test-sampling.cpp
This commit is contained in:
Concedo 2024-12-19 11:57:43 +08:00
commit ee486bad3e
59 changed files with 20531 additions and 13185 deletions
Download patch file Download diff file Expand all files Collapse all files

30
common/common.cpp
View file

@ -942,6 +942,25 @@ struct common_init_result common_init_from_params(common_params & params) {
params.sampling.ignore_eos = false;
}
if (params.sampling.ignore_eos) {
for (llama_token i = 0; i < llama_n_vocab(model); i++) {
if (llama_token_is_eog(model, i)) {
LOG_INF("%s: added %s logit bias = %f\n", __func__, common_token_to_piece(lctx, i).c_str(), -INFINITY);
params.sampling.logit_bias.push_back({i, -INFINITY});
}
}
}
if (params.sampling.penalty_last_n == -1) {
LOG_INF("%s: setting penalty_last_n to ctx_size = %d\n", __func__, llama_n_ctx(lctx));
params.sampling.penalty_last_n = llama_n_ctx(lctx);
}
if (params.sampling.dry_penalty_last_n == -1) {
LOG_INF("%s: setting dry_penalty_last_n to ctx_size = %d\n", __func__, llama_n_ctx(lctx));
params.sampling.dry_penalty_last_n = llama_n_ctx(lctx);
}
if (params.warmup) {
LOG_WRN("%s: warming up the model with an empty run - please wait ... (--no-warmup to disable)\n", __func__);
@ -1078,7 +1097,7 @@ struct ggml_threadpool_params ggml_threadpool_params_from_cpu_params(const cpu_p
#define CURL_MAX_RETRY 3
#define CURL_RETRY_DELAY_SECONDS 2
static bool curl_perform_with_retry(const std::string& url, CURL* curl, int max_attempts, int retry_delay_seconds) {
static bool curl_perform_with_retry(const std::string & url, CURL * curl, int max_attempts, int retry_delay_seconds) {
int remaining_attempts = max_attempts;
while (remaining_attempts > 0) {
@ -1102,7 +1121,6 @@ static bool curl_perform_with_retry(const std::string& url, CURL* curl, int max_
}
static bool common_download_file(const std::string & url, const std::string & path, const std::string & hf_token) {
// Initialize libcurl
std::unique_ptr<CURL, decltype(&curl_easy_cleanup)> curl(curl_easy_init(), &curl_easy_cleanup);
if (!curl) {
@ -1175,11 +1193,13 @@ static bool common_download_file(const std::string & url, const std::string & pa
std::string etag;
std::string last_modified;
};
common_load_model_from_url_headers headers;
{
typedef size_t(*CURLOPT_HEADERFUNCTION_PTR)(char *, size_t, size_t, void *);
auto header_callback = [](char * buffer, size_t /*size*/, size_t n_items, void * userdata) -> size_t {
common_load_model_from_url_headers *headers = (common_load_model_from_url_headers *) userdata;
common_load_model_from_url_headers * headers = (common_load_model_from_url_headers *) userdata;
static std::regex header_regex("([^:]+): (.*)\r\n");
static std::regex etag_regex("ETag", std::regex_constants::icase);
@ -1763,7 +1783,9 @@ void common_embd_normalize(const float * inp, float * out, int n, int embd_norm)
break;
case 0: // max absolute
for (int i = 0; i < n; i++) {
if (sum < std::abs(inp[i])) sum = std::abs(inp[i]);
if (sum < std::abs(inp[i])) {
sum = std::abs(inp[i]);
}
}
sum /= 32760.0; // make an int16 range
break;