yujunjun/FlagEmbedding
1
0
Fork 0
mirror of https://github.com/FlagOpen/FlagEmbedding.git synced 2025-06-27 02:39:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

update m3 example code

Browse Source
This commit is contained in:
hanhainebula 2024-10-19 18:01:31 +08:00
parent 052954588a
commit 4d2916cfe6
2 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
examples/inference/embedder/encoder_only/m3_multi_devices.py
View File

@ -13,12 +13,12 @@ def test_m3_multi_devices():
)
queries = [
"What is BGE M3?",
"Defination of BM25"
"What is the capital of France?",
"What is the population of China?",
] * 100
passages = [
"BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.",
"BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"
"Paris is the capital of France.",
"The population of China is over 1.4 billion people."
] * 100
queries_embeddings = model.encode_queries(

8
examples/inference/embedder/encoder_only/m3_single_device.py
View File

@ -13,12 +13,12 @@ def test_m3_single_devices():
)
queries = [
"What is BGE M3?",
"Defination of BM25"
"What is the capital of France?",
"What is the population of China?",
] * 100
passages = [
"BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.",
"BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"
"Paris is the capital of France.",
"The population of China is over 1.4 billion people."
] * 100
queries_embeddings = model.encode_queries(