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

embedding : more cli arguments (#7458)

Browse source 
* add parameters for embeddings
--embd-normalize
--embd-output-format
--embd-separator
description in the README.md

* Update README.md

fix tipo

* Trailing whitespace

* fix json generation, use " not '

* fix merge master

* fix code formating
group of parameters // embedding
print usage for embedding parameters

---------

Co-authored-by: Brian <mofosyne@gmail.com>
This commit is contained in:
Yann Follet 2024-06-24 13:30:24 +08:00 • committed by GitHub
parent de0d6a68ac
commit 646ef4a9cf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 314 additions and 557 deletions
Download patch file Download diff file Expand all files Collapse all files

9
common/common.h
View file

@ -152,7 +152,6 @@ struct gpt_params {
bool prompt_cache_all = false; // save user input and generations to prompt cache
bool prompt_cache_ro = false; // open the prompt cache read-only and do not update it
bool embedding = false; // get only sentence embedding
bool escape = true; // escape "\n", "\r", "\t", "\'", "\"", and "\\"
bool multiline_input = false; // reverse the usage of `\`
bool simple_io = false; // improves compatibility with subprocesses and limited consoles
@ -179,6 +178,12 @@ struct gpt_params {
std::string mmproj = ""; // path to multimodal projector
std::vector<std::string> image; // path to image file(s)
// embedding
bool embedding = false; // get only sentence embedding
int32_t embd_normalize = 2; // normalisation for embendings (-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 embendings
// server params
int32_t port = 8080; // server listens on this network port
int32_t timeout_read = 600; // http read timeout in seconds
@ -377,7 +382,7 @@ void llama_kv_cache_dump_view_seqs(const llama_kv_cache_view & view, int row_siz
// Embedding utils
//
void llama_embd_normalize(const float * inp, float * out, int n);
void llama_embd_normalize(const float * inp, float * out, int n, int embd_norm = 2);
float llama_embd_similarity_cos(const float * embd1, const float * embd2, int n);