Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 01:31:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/close-issue.yml
#	.github/workflows/nix-ci-aarch64.yml
#	.github/workflows/nix-ci.yml
#	README.md
#	ci/run.sh
#	examples/server/README.md
#	ggml/src/ggml-cuda.cu
#	ggml/src/ggml-metal.m
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo
2024-10-05 22:24:08 +08:00
parent 3e1cbedbae 8c475b97b8
commit da6cf261a8
28 changed files with 725 additions and 421 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+1 -1
View File
@@ -912,7 +912,7 @@ gpt_params_context gpt_params_parser_init(gpt_params & params, llama_example ex,
).set_sparam());
add_opt(llama_arg(
{"-s", "--seed"}, "SEED",
format("RNG seed (default: %u, use random seed for %u)", params.sparams.seed, LLAMA_DEFAULT_SEED),
format("RNG seed (default: %d, use random seed for %d)", params.sparams.seed, LLAMA_DEFAULT_SEED),
[](gpt_params & params, const std::string & value) {
params.sparams.seed = std::stoul(value);
}
common/common.cpp
+29 -1
View File
@@ -840,6 +840,31 @@ struct llama_init_result llama_init_from_gpt_params(gpt_params & params) {
return iparams;
}
if (params.reranking) {
bool ok = true;
if (llama_token_bos(model) == LLAMA_TOKEN_NULL) {
LOG_WRN("%s: warning: model does not have a BOS token, reranking will not work\n", __func__);
ok = false;
}
if (llama_token_eos(model) == LLAMA_TOKEN_NULL) {
LOG_WRN("%s: warning: model does not have an EOS token, reranking will not work\n", __func__);
ok = false;
}
if (llama_token_sep(model) == LLAMA_TOKEN_NULL) {
LOG_WRN("%s: warning: model does not have a SEP token, reranking will not work\n", __func__);
ok = false;
}
if (!ok) {
llama_free_model(model);
return iparams;
}
}
auto cparams = llama_context_params_from_gpt_params(params);
llama_context * lctx = llama_new_context_with_model(model, cparams);
@@ -857,6 +882,7 @@ struct llama_init_result llama_init_from_gpt_params(gpt_params & params) {
if (cvec.n_embd == -1) {
llama_free(lctx);
llama_free_model(model);
return iparams;
}
@@ -869,6 +895,7 @@ struct llama_init_result llama_init_from_gpt_params(gpt_params & params) {
if (err) {
llama_free(lctx);
llama_free_model(model);
return iparams;
}
}
@@ -891,7 +918,7 @@ struct llama_init_result llama_init_from_gpt_params(gpt_params & params) {
llama_lora_adapters_apply(lctx, iparams.lora_adapters);
}
if (params.sparams.ignore_eos && llama_token_eos(model) == -1) {
if (params.sparams.ignore_eos && llama_token_eos(model) == LLAMA_TOKEN_NULL) {
LOG_WRN("%s: warning: model does not have an EOS token, ignoring --ignore-eos\n", __func__);
params.sparams.ignore_eos = false;
}
@@ -932,6 +959,7 @@ struct llama_init_result llama_init_from_gpt_params(gpt_params & params) {
iparams.model = model;
iparams.context = lctx;
return iparams;
}