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
#	.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
commit da6cf261a8
28 changed files with 725 additions and 421 deletions
Download patch file Download diff file Expand all files Collapse all files

30
common/common.cpp
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;
}