happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

server: add missing rerank and chat presets (#10932)

This commit is contained in:
ingyukoh 2026-01-11 01:44:36 +09:00
parent 9ac2693a30
commit 9882f21ab9
1 changed files with 24 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
common/arg.cpp
View File

@ -3505,6 +3505,30 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples({LLAMA_EXAMPLE_TTS}));
add_opt(common_arg(
{"--rerank-bge-m3-default"},
string_format("use BAAI/bge-reranker-v2-m3 (note: can download weights from the internet)"),
[](common_params & params) {
params.model.hf_repo = "BAAI/bge-reranker-v2-m3";
params.model.hf_file = "bge-reranker-v2-m3-Q8_0.gguf";
params.embedding = true;
params.port = 8015;
}
).set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--chat-llama3.1-8b-default"},
string_format("use Meta Llama 3.1 8B Instruct (note: can download weights from the internet)"),
[](common_params & params) {
params.model.hf_repo = "gaianet/Meta-Llama-3.1-8B-Instruct-GGUF";
params.model.hf_file = "Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf";
params.port = 8016;
params.n_ubatch = 512;
params.n_batch = 2048;
params.n_ctx = 8192;
}
).set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--embd-gemma-default"},
string_format("use default EmbeddingGemma model (note: can download weights from the internet)"),