Sentence Similarity
sentence-transformers
PyTorch
TensorFlow
Rust
ONNX
Safetensors
OpenVINO
Transformers
English
bert
feature-extraction
Eval Results
text-embeddings-inference
Instructions to use sentence-transformers/all-MiniLM-L6-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use sentence-transformers/all-MiniLM-L6-v2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use sentence-transformers/all-MiniLM-L6-v2 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/all-MiniLM-L6-v2") model = AutoModel.from_pretrained("sentence-transformers/all-MiniLM-L6-v2") - Inference
- Notebooks
- Google Colab
- Kaggle
Unable to load sentence transformer ( was previously working)
1
#98 opened over 1 year ago
by
avifin19
Should I be concerned about "UserWarning: TypedStorage is deprecated. " when using the model with python 3.11?
1
#97 opened over 1 year ago
by
poohlio
Add openvino converted tokenizers
2
#96 opened over 1 year ago
by
rhecker
Unable to Generate Non-Normalized Embeddings with Sentence-Transformers
#95 opened over 1 year ago
by
ArthurGprog
Support for Tensorflow.js
2
#94 opened over 1 year ago
by
bayang
Request: DOI
#93 opened over 1 year ago
by
Lamurian
Update 1_Pooling/config.json
#92 opened over 1 year ago
by
michaelfeil
Guide for creating openvino and qint8 for hf model
7
#89 opened over 1 year ago
by
bayang
ζ―ζδΈζε
5
#88 opened over 1 year ago
by
hswu
ONNX Models
2
#82 opened almost 2 years ago
by
ha1772007
Request: DOI
#81 opened almost 2 years ago
by
aryanagal
Hyperparameter tuning using Sagemaker
1
#80 opened almost 2 years ago
by
caz4dora
Similarity Search Type
1
#77 opened almost 2 years ago
by
frbackup
Truncating Text
2
#76 opened almost 2 years ago
by
frbackup
Trying to run this model locally, on my machine
4
#75 opened almost 2 years ago
by
abdulrafay97
Conversion to Tensorflow lite
π₯ 2
1
#74 opened almost 2 years ago
by
mhdhrubo
Why is an Opensource OS like FreeBSD not supported ?
#73 opened almost 2 years ago
by
Leyor88
can I use api to get the embeddings?
7
#72 opened almost 2 years ago
by
starmaq
I'm trying to run this model in the browser using wonnx, but it isn't working
1
#71 opened about 2 years ago
by
jhqcat
Does the model take our data and use our data to improve itself or for some other purpose?
2
#70 opened about 2 years ago
by
AIProDK
Request: DOI
1
#69 opened about 2 years ago
by
aaravjaichand
Request: DOI
1
#68 opened about 2 years ago
by
bbaiatu
Onnx model doesn't produce embeddings close enough to SentenceTransformer version
6
#67 opened about 2 years ago
by
luciancap001
Model Card describes input size as 256 but Tokenizer is using 512 & output names of model changed
4
#66 opened about 2 years ago
by
luciancap001
512 seq length version
ππ 1
#65 opened about 2 years ago
by
nbroad
Semantic similarity between two texts !
2
#63 opened about 2 years ago
by
Systeme
BetterTransformer
#62 opened about 2 years ago
by
Gerald001
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host
1
#61 opened about 2 years ago
by
caleb425
[AUTOMATED] Model Memory Requirements
#60 opened about 2 years ago
by
model-sizer-bot
Comparison to all-MiniLM-L12-v2
#58 opened about 2 years ago
by
swax-andres
Matching pdf with keywords
#57 opened about 2 years ago
by
DevSelego
Can't load the configuration of 'sentence-transformers/all-MiniLM-L6-v2'
1
#55 opened over 2 years ago
by
stleandro
Embeddings quality for inputs longer than 128 tokens
2
#52 opened over 2 years ago
by
HiddenGaze
Has all-MiniLM-L6-v2 ever changed it's architecture? I have two different models
2
#49 opened over 2 years ago
by
rcland12
π© Report: Ethical issue(s)
#45 opened over 2 years ago
by
willzh123
model in closed network
4
#43 opened over 2 years ago
by
iamwhoiamm
sentence similarity between spacy and sentence-transformer
2
#42 opened over 2 years ago
by
YouXiang
Memory is becoming fully exhausted during the generation of embeddings, leading to a complete server crash.
4
#41 opened over 2 years ago
by
vobbilisettyjayadeep
Adding ONNX file of this model
π 1
1
#40 opened over 2 years ago
by
TDK2434
[AUTOMATED] Model Memory Requirements
π 2
#39 opened over 2 years ago
by
model-sizer-bot
input embeddings, output similarity. Can this be done through an inference endpoint?
2
#38 opened over 2 years ago
by
click37
Do these semantic sentence embeddings produce better results than semantic word embeddings?
4
#37 opened over 2 years ago
by
austincap
Can I calculate the sentence similarity for the French text?
#36 opened over 2 years ago
by
Leiding
Segmentation Fault
π 3
1
#35 opened over 2 years ago
by
loretoparisi
License and commercial usage
π 5
1
#34 opened almost 3 years ago
by
simkes
German Use Case
2
#33 opened almost 3 years ago
by
jdjayakaran
How do I convert the model into tflite and use it for sentence similarity
#31 opened almost 3 years ago
by
Aniruddh232002
Request: DOI
π 4
#30 opened almost 3 years ago
by
samuelelotruglio
How can I get the first element of model_output from the second element?
#27 opened almost 3 years ago
by
LinPeisensh