CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

server: fix reported top tokens for temperature 0 (#7203)

Browse Source
This commit is contained in:
Johannes Gäßler
2024-05-11 10:11:28 +02:00
committed by GitHub
parent b83cc3f5b3
commit 5ae3426b0b
3 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/server/server.cpp
View File

@@ -2270,10 +2270,10 @@ struct server_context {
const size_t n_probs = std::min(cur_p.size, (size_t) slot.sparams.n_probs);
if (n_probs > 0) {
const size_t n_considered = slot.ctx_sampling->n_considered;
const size_t n_valid = slot.ctx_sampling->n_valid;
// Make sure at least n_probs top tokens are at the front of the vector:
if (slot.sparams.temp == 0.0f && n_probs > n_considered) {
if (slot.sparams.temp == 0.0f && n_probs > n_valid) {
llama_sample_top_k(ctx, &cur_p, n_probs, 0);
}
@@ -2289,7 +2289,7 @@ struct server_context {
for (size_t i = 0; i < n_probs; ++i) {
result.probs.push_back({
cur_p.data[i].id,
i >= n_considered ? 0.0f : cur_p.data[i].p // Tokens filtered out due to e.g. top_k have 0 probability.
i >= n_valid ? 0.0f : cur_p.data[i].p // Tokens filtered out due to e.g. top_k have 0 probability.
});
}
}