vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	examples/run/run.cpp
#	scripts/sync-ggml.last
This commit is contained in:
Concedo 2025-02-08 01:31:49 +08:00
commit 27b9358baf
12 changed files with 181 additions and 135 deletions
Download patch file Download diff file Expand all files Collapse all files

42
common/arg.cpp
View file

@ -2325,5 +2325,47 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples({LLAMA_EXAMPLE_TTS}));
add_opt(common_arg(
{"--embd-bge-small-en-default"},
string_format("use default bge-small-en-v1.5 model (note: can download weights from the internet)"),
[](common_params & params) {
params.hf_repo = "ggml-org/bge-small-en-v1.5-Q8_0-GGUF";
params.hf_file = "bge-small-en-v1.5-q8_0.gguf";
params.pooling_type = LLAMA_POOLING_TYPE_NONE;
params.embd_normalize = 2;
params.n_ctx = 512;
params.verbose_prompt = true;
params.embedding = true;
}
).set_examples({LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--embd-e5-small-en-default"},
string_format("use default e5-small-v2 model (note: can download weights from the internet)"),
[](common_params & params) {
params.hf_repo = "ggml-org/e5-small-v2-Q8_0-GGUF";
params.hf_file = "e5-small-v2-q8_0.gguf";
params.pooling_type = LLAMA_POOLING_TYPE_NONE;
params.embd_normalize = 2;
params.n_ctx = 512;
params.verbose_prompt = true;
params.embedding = true;
}
).set_examples({LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--embd-gte-small-default"},
string_format("use default gte-small model (note: can download weights from the internet)"),
[](common_params & params) {
params.hf_repo = "ggml-org/gte-small-Q8_0-GGUF";
params.hf_file = "gte-small-q8_0.gguf";
params.pooling_type = LLAMA_POOLING_TYPE_NONE;
params.embd_normalize = 2;
params.n_ctx = 512;
params.verbose_prompt = true;
params.embedding = true;
}
).set_examples({LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_SERVER}));
return ctx_arg;
}