root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-28 04:14:35 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

ppl : fix n_seq_max for perplexity

Browse Source
This commit is contained in:
slaren 2024-07-03 16:10:36 +02:00
parent 916248af1f
commit 5cf23d11c8
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
examples/perplexity/perplexity.cpp
View File

@ -1991,6 +1991,8 @@ int main(int argc, char ** argv) {
params.n_batch = std::min(params.n_batch, n_kv); params.n_batch = std::min(params.n_batch, n_kv);
} else { } else {
params.n_batch = std::min(params.n_batch, params.n_ctx); params.n_batch = std::min(params.n_batch, params.n_ctx);
// ensure there's at least enough seq_ids for HellaSwag
params.n_parallel = std::max(4, params.n_parallel);
} }
if (params.ppl_stride > 0) { if (params.ppl_stride > 0) {
@ -2015,9 +2017,6 @@ int main(int argc, char ** argv) {
llama_model * model; llama_model * model;
llama_context * ctx; llama_context * ctx;
// ensure there's at least enough seq_ids for HellaSwag
params.n_parallel = std::max(4, params.n_parallel);
// load the model and apply lora adapter, if any // load the model and apply lora adapter, if any
std::tie(model, ctx) = llama_init_from_gpt_params(params); std::tie(model, ctx) = llama_init_from_gpt_params(params);
if (model == NULL) { if (model == NULL) {