ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : improve sep token handling (#14272)

Browse source
This commit is contained in:
Sigbjørn Skjæret 2025-06-20 14:04:09 +02:00 • committed by GitHub
parent e28c1b93fd
commit 88fc854b4b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 161 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

7
common/arg.cpp
View file

@ -2706,6 +2706,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.embd_sep = value;
}
).set_examples({LLAMA_EXAMPLE_EMBEDDING}));
add_opt(common_arg(
{"--cls-separator"}, "STRING",
"separator of classification sequences (default \\t) for example \"<#seq#>\"",
[](common_params & params, const std::string & value) {
params.cls_sep = value;
}
).set_examples({LLAMA_EXAMPLE_EMBEDDING}));
add_opt(common_arg(
{"--host"}, "HOST",
string_format("ip address to listen, or bind to an UNIX socket if the address ends with .sock (default: %s)", params.hostname.c_str()),

1
common/common.h
View file

@ -358,6 +358,7 @@ struct common_params {
int32_t embd_normalize = 2; // normalisation for embeddings (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm)
std::string embd_out = ""; // empty = default, "array" = [[],[]...], "json" = openai style, "json+" = same "json" + cosine similarity matrix
std::string embd_sep = "\n"; // separator of embeddings
std::string cls_sep = "\t"; // separator of classification sequences
// server params
int32_t port = 8080; // server listens on this network port