vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	common/sampling.h
#	llama.h
#	tests/test-chat-template.cpp
This commit is contained in:
Concedo 2024-04-24 21:29:07 +08:00
commit a681cdd9ef
20 changed files with 788 additions and 355 deletions
Download patch file Download diff file Expand all files Collapse all files

5
examples/server/server.cpp
View file

@ -855,7 +855,7 @@ struct server_context {
slot.sparams.penalize_nl = json_value(data, "penalize_nl", default_sparams.penalize_nl);
slot.params.n_keep = json_value(data, "n_keep", slot.params.n_keep);
slot.params.n_discard = json_value(data, "n_discard", default_params.n_discard);
slot.params.seed = json_value(data, "seed", default_params.seed);
slot.sparams.seed = json_value(data, "seed", default_sparams.seed);
slot.sparams.n_probs = json_value(data, "n_probs", default_sparams.n_probs);
slot.sparams.min_keep = json_value(data, "min_keep", default_sparams.min_keep);
@ -1029,7 +1029,6 @@ struct server_context {
send_error(task, "Failed to parse grammar", ERROR_TYPE_INVALID_REQUEST);
return false;
}
llama_set_rng_seed(ctx, slot.params.seed);
}
slot.command = SLOT_COMMAND_LOAD_PROMPT;
@ -1119,7 +1118,7 @@ struct server_context {
bool process_token(completion_token_output & result, server_slot & slot) {
// remember which tokens were sampled - used for repetition penalties during sampling
const std::string token_str = llama_token_to_piece(ctx, result.tok);
const std::string token_str = llama_token_to_piece(ctx, result.tok, false);
slot.sampled = result.tok;
// search stop word and delete it