vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/full-rocm.Dockerfile
#	.devops/full.Dockerfile
#	.devops/llama-cpp-clblast.srpm.spec
#	.devops/llama-cpp-cuda.srpm.spec
#	.devops/llama-cpp.srpm.spec
#	.devops/nix/package.nix
#	.devops/server-cuda.Dockerfile
#	.devops/server-intel.Dockerfile
#	.devops/server-rocm.Dockerfile
#	.devops/server-vulkan.Dockerfile
#	.devops/server.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/code-coverage.yml
#	.github/workflows/docker.yml
#	.github/workflows/editorconfig.yml
#	.github/workflows/gguf-publish.yml
#	.github/workflows/nix-ci-aarch64.yml
#	.github/workflows/nix-ci.yml
#	.github/workflows/python-check-requirements.yml
#	.github/workflows/python-lint.yml
#	.github/workflows/server.yml
#	.github/workflows/zig-build.yml
#	CMakeLists.txt
#	Makefile
#	README-sycl.md
#	README.md
#	ci/run.sh
#	examples/gguf-split/gguf-split.cpp
#	flake.lock
#	flake.nix
#	llama.cpp
#	scripts/compare-llama-bench.py
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.last
#	scripts/sync-ggml.sh
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
This commit is contained in:
Concedo 2024-04-07 22:07:27 +08:00
commit 81ac0e5656
58 changed files with 32809 additions and 7635 deletions
Download patch file Download diff file Expand all files Collapse all files

13
common/common.cpp
View file

@ -1063,8 +1063,8 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.ignore_eos = true;
return true;
}
if (arg == "--no-penalize-nl") {
sparams.penalize_nl = false;
if (arg == "--penalize-nl") {
sparams.penalize_nl = true;
return true;
}
if (arg == "-l" || arg == "--logit-bias") {
@ -1374,7 +1374,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" -dt N, --defrag-thold N\n");
printf(" KV cache defragmentation threshold (default: %.1f, < 0 - disabled)\n", params.defrag_thold);
printf(" --ignore-eos ignore end of stream token and continue generating (implies --logit-bias 2-inf)\n");
printf(" --no-penalize-nl do not penalize newline token\n");
printf(" --penalize-nl penalize newline tokens\n");
printf(" --temp N temperature (default: %.1f)\n", (double)sparams.temp);
printf(" --all-logits return logits for all tokens in the batch (default: disabled)\n");
printf(" --hellaswag compute HellaSwag score over random tasks from datafile supplied with -f\n");
@ -1929,11 +1929,6 @@ struct llama_model * llama_load_model_from_url(
return NULL;
}
if (!curl) {
fprintf(stderr, "%s: error initializing libcurl\n", __func__);
return NULL;
}
if (!llama_download_file(curl, model_url, path_model)) {
return NULL;
}
@ -2490,7 +2485,7 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l
fprintf(stream, "n_predict: %d # default: -1 (unlimited)\n", params.n_predict);
fprintf(stream, "n_probs: %d # only used by server binary, default: 0\n", sparams.n_probs);
fprintf(stream, "no_mmap: %s # default: false\n", !params.use_mmap ? "true" : "false");
fprintf(stream, "no_penalize_nl: %s # default: false\n", !sparams.penalize_nl ? "true" : "false");
fprintf(stream, "penalize_nl: %s # default: false\n", sparams.penalize_nl ? "true" : "false");
fprintf(stream, "ppl_output_type: %d # default: 0\n", params.ppl_output_type);
fprintf(stream, "ppl_stride: %d # default: 0\n", params.ppl_stride);
fprintf(stream, "presence_penalty: %f # default: 0.0\n", sparams.penalty_present);