tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Perplexity: Compute scores correlated to HellaSwag (#2312)

Browse Source 
* Add parameter --perplexity-lines to perplexity.cpp
This commit is contained in:
klosax
2023-07-22 14:21:24 +02:00
committed by GitHub
parent 24baa54ac1
commit b5fe67f8c6
3 changed files with 82 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/common.cpp
View File

@ -387,6 +387,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
params.antiprompt.push_back(argv[i]);
} else if (arg == "--perplexity") {
params.perplexity = true;
} else if (arg == "--perplexity-lines") {
params.perplexity_lines = true;
} else if (arg == "--ignore-eos") {
params.logit_bias[llama_token_eos()] = -INFINITY;
} else if (arg == "--no-penalize-nl") {
@ -512,7 +514,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stderr, " not recommended: doubles context memory required and no measurable increase in quality\n");
fprintf(stderr, " --temp N temperature (default: %.1f)\n", (double)params.temp);
fprintf(stderr, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
fprintf(stderr, " --perplexity compute perplexity over the prompt\n");
fprintf(stderr, " --perplexity compute perplexity over each ctx window of the prompt\n");
fprintf(stderr, " --perplexity-lines compute perplexity over each line of the prompt\n");
fprintf(stderr, " --keep number of tokens to keep from the initial prompt (default: %d, -1 = all)\n", params.n_keep);
fprintf(stderr, " --chunks N max number of chunks to process (default: %d, -1 = all)\n", params.n_chunks);
if (llama_mlock_supported()) {