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

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-12-17 10:56:20 +02:00
parent 89eaf5036a
commit 06e85401b0
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/server/tests/utils.py
View file

@ -275,7 +275,7 @@ class ServerPreset:
return server return server
@staticmethod @staticmethod
def bert_bge_small() -> ServerProcess: def bert_bge_small(pooling = 'last') -> ServerProcess:
server = ServerProcess() server = ServerProcess()
server.model_hf_repo = "ggml-org/models" server.model_hf_repo = "ggml-org/models"
server.model_hf_file = "bert-bge-small/ggml-model-f16.gguf" server.model_hf_file = "bert-bge-small/ggml-model-f16.gguf"
@ -286,6 +286,7 @@ class ServerPreset:
server.n_slots = 2 server.n_slots = 2
server.seed = 42 server.seed = 42
server.server_embeddings = True server.server_embeddings = True
server.pooling = pooling
return server return server
@staticmethod @staticmethod