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

server : output embeddings for all tokens when pooling = none (#10861)

Browse source 
* server : add "tokens" output

ggml-ci

* server : output embeddings for all tokens when pooling = none

ggml-ci

* server : update readme [no ci]

* server : fix spacing [no ci]

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* server : be explicit about the pooling type in the tests

ggml-ci

* server : update /embeddings and /v1/embeddings endpoints

ggml-ci

* server : do not normalize embeddings when there is no pooling

ggml-ci

* server : update readme

ggml-ci

* server : fixes

* tests : update server tests

ggml-ci

* server : update readme [no ci]

* server : remove rebase artifact

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Georgi Gerganov 2024-12-18 13:01:41 +02:00 • committed by GitHub
parent 0e70ba686e
commit 152610eda9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 158 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/gritlm/gritlm.cpp
View file

@ -75,7 +75,7 @@ static std::vector<std::vector<float>> encode(llama_context * ctx, const std::ve
}
std::vector<float> emb_norm(emb_unorm.size());
common_embd_normalize(emb_unorm.data(), emb_norm.data(), n_embd);
common_embd_normalize(emb_unorm.data(), emb_norm.data(), n_embd, 2);
result.push_back(emb_norm);
#ifdef GRIT_DEBUG