Sentence Similarity
sentence-transformers
Safetensors
English
bert
feature-extraction
Generated from Trainer
dataset_size:942069
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use sobamchan/bert-base-uncased-mean-softmax-100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use sobamchan/bert-base-uncased-mean-softmax-100 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("sobamchan/bert-base-uncased-mean-softmax-100") sentences = [ "Two women having drinks and smoking cigarettes at the bar.", "Women are celebrating at a bar.", "Two kids are outdoors.", "The four girls are attending the street festival." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download rng_state.pth from sobamchan/bert-base-uncased-mean-softmax-100: direct link, hf CLI and curl.
- Browser
- Download file 14.2 kB
-
https://huggingface.co/sobamchan/bert-base-uncased-mean-softmax-100/resolve/main/rng_state.pth
- Command line
-
hf download hf://sobamchan/bert-base-uncased-mean-softmax-100/rng_state.pth
-
curl -L -o rng_state.pth https://huggingface.co/sobamchan/bert-base-uncased-mean-softmax-100/resolve/main/rng_state.pth
14.2 kB
- Xet hash:
- 42eefde8c1d09a9de89ab538c03b2bfb7880435105993ed50bb1a1ef2e427b97
- Size of remote file:
- 14.2 kB
- SHA256:
- 58c848be826f62dde34b5e375d482c422f739ea3a9582b6e0ca824aa8f4908bc
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.