sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-10 11:04:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

allow to toggle embedding mode

Browse Source
This commit is contained in:
Douglas Hanley
2024-03-07 11:55:27 -06:00
parent f618e5060a
commit bd3d9fbfed
5 changed files with 21 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
common/common.cpp
View File

@@ -1304,7 +1304,6 @@ struct llama_context_params llama_context_params_from_gpt_params(const gpt_param
cparams.pooling_type = params.pooling_type;
cparams.defrag_thold = params.defrag_thold;
cparams.offload_kqv = !params.no_kv_offload;
cparams.causal_attn = !params.embedding;
cparams.type_k = kv_cache_type_from_str(params.cache_type_k);
cparams.type_v = kv_cache_type_from_str(params.cache_type_v);