py : add XLMRobertaForSequenceClassification [no ci]
3453e62b
py : fix scalar-tensor conversion [no ci]
77723ed6
py : fix position embeddings chop [no ci]
49f90de3
llama : read new cls tensors [no ci]
dc0cdd87
llama : add classigication head (wip) [no ci]
d0a7bf93
llama : add "rank" pooling type
125a0671
server : add rerank endpoint
6235c62a
llama : aboud ggml_repeat during classification
6916ed16
rerank : cleanup + comments
62a45d12
server : accept /rerank endpoint in addition to /v1/rerank [no ci]
7bde9a04
embedding : parse special tokens
c62a39d9
jina : support v1 reranker
866c0113
vocab : minor style
84f56f3c
server : initiate tests for later
00b33760
server : add docs
877a04cc
llama : add comment [no ci]
4d457755
llama : fix uninitialized tensors
ca99a6ce
ci : add rerank tests
f19554f4
add reranking test
f27dd699
change test data
1ae8376d
ngxson
commented
on 2024-09-26
Update examples/server/server.cpp
84b0af83
add `--reranking` argument
0d6f6a79
update server docs
a4ac45f6
llama : fix comment [no ci]
39167b69
Merge branch 'master' into gg/rerank
aeac8768
Reviewers
Assignees
No one assigned
Labels
examples
python
devops
server
merge ready
Milestone
No milestone
Login to write a write a comment.
Login via GitHub