CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

common : change --no-penalize-nl to --penalize-nl (#6334)

Browse Source 
* Change --no-penalize-nl to --penalize-nl

* Update documentation too
This commit is contained in:
Sigbjørn Skjæret
2024-03-27 08:23:10 +01:00
committed by GitHub
parent 2ab4f00d25
commit e562b9714b
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
common/common.cpp
View File

@@ -1062,8 +1062,8 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.ignore_eos = true; params.ignore_eos = true;
return true; return true;
} }
if (arg == "--no-penalize-nl") { if (arg == "--penalize-nl") {
sparams.penalize_nl = false; sparams.penalize_nl = true;
return true; return true;
} }
if (arg == "-l" || arg == "--logit-bias") { if (arg == "-l" || arg == "--logit-bias") {
@@ -1373,7 +1373,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" -dt N, --defrag-thold N\n"); printf(" -dt N, --defrag-thold N\n");
printf(" KV cache defragmentation threshold (default: %.1f, < 0 - disabled)\n", params.defrag_thold); 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(" --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(" --temp N temperature (default: %.1f)\n", (double)sparams.temp);
printf(" --all-logits return logits for all tokens in the batch (default: disabled)\n"); 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"); printf(" --hellaswag compute HellaSwag score over random tasks from datafile supplied with -f\n");
@@ -2489,7 +2489,7 @@ 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_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, "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_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_output_type: %d # default: 0\n", params.ppl_output_type);
fprintf(stream, "ppl_stride: %d # default: 0\n", params.ppl_stride); fprintf(stream, "ppl_stride: %d # default: 0\n", params.ppl_stride);
fprintf(stream, "presence_penalty: %f # default: 0.0\n", sparams.penalty_present); fprintf(stream, "presence_penalty: %f # default: 0.0\n", sparams.penalty_present);