README.md

---
title: README
emoji: ❤️
colorFrom: red
colorTo: red
sdk: static
pinned: false
---
<div class="lg:col-span-3">
   <p class="mb-4">
      SentenceTransformers 🤗 is a Python framework for state-of-the-art sentence, text and image embeddings. 
   </p>
   <p class="mb-4">
      Install the <a
         href="https://www.sbert.net/"
         >Sentence Transformers</a
         >
      library.
   </p>
   <div
      class="p-4 bg-gradient-to-b from-gray-50-to-white border border-gray-100 rounded-lg relative mb-4"
      >
      <pre class="break-words leading-1 whitespace-pre-line text-xs md:text-sm text-gray-800">
	pip install -U sentence-transformers
		</pre>
   </div>
   </p>
   <div class="lg:col-span-3">
      <p class="mb-4">
         The usage is as simple as:
      </p>
      <div
         class="p-4 bg-gradient-to-b from-gray-50-to-white border border-gray-100 rounded-lg relative mb-4"
         >
         <pre class="break-words leading-1 whitespace-pre-line text-xs md:text-sm text-gray-800">           
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('paraphrase-MiniLM-L6-v2')

#Sentences we want to encode. Example:
sentence = ['This framework generates embeddings for each input sentence']

#Sentences are encoded by calling model.encode()
embedding = model.encode(sentence)
</pre>
      </div>
   </div>
</div>
<div class="grid lg:grid-cols-3 gap-x-4 gap-y-7">
<div class="lg:col-span-3">
   <p class="mb-4">
      Hugging Face makes it easy to collaboratively build and showcase your <a
         href="https://www.sbert.net/">Sentence Transformers</a
         >
      models! You can collaborate with your organization, upload and showcase your own models in your profile ❤️
   </p>
</div>
<a href="https://www.sbert.net/" class="block overflow-hidden group">
   <div
      class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center bg-[#FA8072]"
      >
      <img alt="" src="https://huggingface.co/spaces/sentence-transformers/README/resolve/main/sbertLogo.png" class="w-40" />
   </div>
   <div class="underline">Documentation</div>
</a>
<a
   href="https://github.com/UKPLab/sentence-transformers/blob/master/sentence_transformers/SentenceTransformer.py#L417"
   class="block overflow-hidden group"
   >
   <div
      class="w-full h-40 mb-2 bg-gray-900 group-hover:bg-gray-850 rounded-lg flex items-start justify-start overflow-hidden"
      >
      <img
         alt=""
         src="https://huggingface.co/spaces/sentence-transformers/README/resolve/main/push-to-hub.png"
         class="w-full h-40 object-cover overflow-hidden"
         />
   </div>
   <div class="underline">Push your Sentence Transformers models to the Hub ❤️ </div>
</a>
<a
   href="https://huggingface.co/models?library=sentence-transformers&sort=downloads"
   class="block overflow-hidden group"
   >
   <div
      class="w-full h-40 mb-2 bg-gray-900 group-hover:bg-gray-850 rounded-lg flex items-start justify-start overflow-hidden"
      >
      <img
         alt=""
         src="https://huggingface.co/spaces/sentence-transformers/README/resolve/main/sbert-hf.png"
         class="w-full h-40 object-cover overflow-hidden"
         />
   </div>
   <div class="underline">Find all Sentence Transformers models on the 🤗 Hub</div>
</a>
<div class="lg:col-span-3">
   <p class="mb-4">
      To upload your Sentence Transformers models to the Hugging Face Hub log in with <code class="language-python">huggingface-cli login</code> and then use the <a
         href="https://github.com/UKPLab/sentence-transformers/blob/master/sentence_transformers/SentenceTransformer.py#L417"
         >save_to_hub</a
         >
      function within the Sentence Transformers library.
   </p>
   <div
      class="p-4 bg-gradient-to-b from-gray-50-to-white border border-gray-100 rounded-lg relative mb-4"
      >
      <pre
         class="break-words leading-1 whitespace-pre-line text-xs md:text-sm text-gray-800">
	from sentence_transformers import SentenceTransformer
	
	# Load or train a model
	model = ...
	# Push to Hub
	model.save_to_hub("my_new_model")
		</pre>
   </div>
   </p>
</div>