CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/refactor-kv-cache

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-07-04 17:33:52 -04:00
parent 10c3c419e9 d7fd29fff1
commit 9b38f8bf65
102 changed files with 4745 additions and 1675 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/perplexity/perplexity.cpp
View File

@@ -1991,6 +1991,12 @@ int main(int argc, char ** argv) {
params.n_batch = std::min(params.n_batch, n_kv);
} else {
params.n_batch = std::min(params.n_batch, params.n_ctx);
if (params.kl_divergence) {
params.n_parallel = 1;
} else {
// ensure there's at least enough seq_ids for HellaSwag
params.n_parallel = std::max(4, params.n_parallel);
}
}
if (params.ppl_stride > 0) {
@@ -2015,9 +2021,6 @@ int main(int argc, char ** argv) {
llama_model * model;
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
std::tie(model, ctx) = llama_init_from_gpt_params(params);
if (model == NULL) {