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 duplicated n_predict key in the generation_settings (#8994)

Browse Source
This commit is contained in:
Riceball LEE
2024-08-15 15:28:05 +08:00
committed by GitHub
parent 4af8420afb
commit 37501d9c79
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/server.cpp
View File

@@ -1321,7 +1321,7 @@ struct server_context {
return json {
{"n_ctx", slot.n_ctx},
{"n_predict", slot.n_predict},
{"n_predict", slot.n_predict}, // Server configured n_predict
{"model", params.model_alias},
{"seed", slot.sparams.seed},
{"temperature", slot.sparams.temp},
@@ -1343,7 +1343,7 @@ struct server_context {
{"mirostat_eta", slot.sparams.mirostat_eta},
{"penalize_nl", slot.sparams.penalize_nl},
{"stop", slot.params.antiprompt},
{"n_predict", slot.params.n_predict}, // TODO: fix duplicate key n_predict
{"max_tokens", slot.params.n_predict}, // User configured n_predict
{"n_keep", slot.params.n_keep},
{"n_discard", slot.params.n_discard},
{"ignore_eos", ignore_eos},