Awesome
Transformers.rb
:slightly_smiling_face: State-of-the-art transformers for Ruby
For fast inference, check out Informers :fire:
Installation
First, install Torch.rb.
Then add this line to your application’s Gemfile:
gem "transformers-rb"
Getting Started
Models
Embedding
- sentence-transformers/all-MiniLM-L6-v2
- sentence-transformers/multi-qa-MiniLM-L6-cos-v1
- sentence-transformers/all-mpnet-base-v2
- sentence-transformers/paraphrase-MiniLM-L6-v2
- mixedbread-ai/mxbai-embed-large-v1
- thenlper/gte-small
- intfloat/e5-base-v2
- BAAI/bge-base-en-v1.5
- Snowflake/snowflake-arctic-embed-m-v1.5
Sparse embedding
Reranking
sentence-transformers/all-MiniLM-L6-v2
sentences = ["This is an example sentence", "Each sentence is converted"]
model = Transformers.pipeline("embedding", "sentence-transformers/all-MiniLM-L6-v2")
embeddings = model.(sentences)
sentence-transformers/multi-qa-MiniLM-L6-cos-v1
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
model = Transformers.pipeline("embedding", "sentence-transformers/multi-qa-MiniLM-L6-cos-v1")
query_embedding = model.(query)
doc_embeddings = model.(docs)
scores = doc_embeddings.map { |e| e.zip(query_embedding).sum { |d, q| d * q } }
doc_score_pairs = docs.zip(scores).sort_by { |d, s| -s }
sentence-transformers/all-mpnet-base-v2
sentences = ["This is an example sentence", "Each sentence is converted"]
model = Transformers.pipeline("embedding", "sentence-transformers/all-mpnet-base-v2")
embeddings = model.(sentences)
sentence-transformers/paraphrase-MiniLM-L6-v2
sentences = ["This is an example sentence", "Each sentence is converted"]
model = Transformers.pipeline("embedding", "sentence-transformers/paraphrase-MiniLM-L6-v2")
embeddings = model.(sentences)
mixedbread-ai/mxbai-embed-large-v1
query_prefix = "Represent this sentence for searching relevant passages: "
input = [
"The dog is barking",
"The cat is purring",
query_prefix + "puppy"
]
model = Transformers.pipeline("embedding", "mixedbread-ai/mxbai-embed-large-v1")
embeddings = model.(input)
thenlper/gte-small
sentences = ["That is a happy person", "That is a very happy person"]
model = Transformers.pipeline("embedding", "thenlper/gte-small")
embeddings = model.(sentences)
intfloat/e5-base-v2
doc_prefix = "passage: "
query_prefix = "query: "
input = [
doc_prefix + "Ruby is a programming language created by Matz",
query_prefix + "Ruby creator"
]
model = Transformers.pipeline("embedding", "intfloat/e5-base-v2")
embeddings = model.(input)
BAAI/bge-base-en-v1.5
query_prefix = "Represent this sentence for searching relevant passages: "
input = [
"The dog is barking",
"The cat is purring",
query_prefix + "puppy"
]
model = Transformers.pipeline("embedding", "BAAI/bge-base-en-v1.5")
embeddings = model.(input)
Snowflake/snowflake-arctic-embed-m-v1.5
query_prefix = "Represent this sentence for searching relevant passages: "
input = [
"The dog is barking",
"The cat is purring",
query_prefix + "puppy"
]
model = Transformers.pipeline("embedding", "Snowflake/snowflake-arctic-embed-m-v1.5")
embeddings = model.(input, pooling: "cls")
opensearch-project/opensearch-neural-sparse-encoding-v1
docs = ["The dog is barking", "The cat is purring", "The bear is growling"]
model_id = "opensearch-project/opensearch-neural-sparse-encoding-v1"
model = Transformers::AutoModelForMaskedLM.from_pretrained(model_id)
tokenizer = Transformers::AutoTokenizer.from_pretrained(model_id)
special_token_ids = tokenizer.special_tokens_map.map { |_, token| tokenizer.vocab[token] }
feature = tokenizer.(docs, padding: true, truncation: true, return_tensors: "pt", return_token_type_ids: false)
output = model.(**feature)[0]
values, _ = Torch.max(output * feature[:attention_mask].unsqueeze(-1), dim: 1)
values = Torch.log(1 + Torch.relu(values))
values[0.., special_token_ids] = 0
embeddings = values.to_a
mixedbread-ai/mxbai-rerank-base-v1
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
model = Transformers.pipeline("reranking", "mixedbread-ai/mxbai-rerank-base-v1")
result = model.(query, docs)
BAAI/bge-reranker-base
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
model = Transformers.pipeline("reranking", "BAAI/bge-reranker-base")
result = model.(query, docs)
Pipelines
Text
Embedding
embed = Transformers.pipeline("embedding")
embed.("We are very happy to show you the 🤗 Transformers library.")
Reranking
rerank = Informers.pipeline("reranking")
rerank.("Who created Ruby?", ["Matz created Ruby", "Another doc"])
Named-entity recognition
ner = Transformers.pipeline("ner")
ner.("Ruby is a programming language created by Matz")
Sentiment analysis
classifier = Transformers.pipeline("sentiment-analysis")
classifier.("We are very happy to show you the 🤗 Transformers library.")
Question answering
qa = Transformers.pipeline("question-answering")
qa.(question: "Who invented Ruby?", context: "Ruby is a programming language created by Matz")
Feature extraction
extractor = Transformers.pipeline("feature-extraction")
extractor.("We are very happy to show you the 🤗 Transformers library.")
Vision
Image classification
classifier = Transformers.pipeline("image-classification")
classifier.("image.jpg")
Image feature extraction
extractor = Transformers.pipeline("image-feature-extraction")
extractor.("image.jpg")
API
This library follows the Transformers Python API. The following model architectures are currently supported:
- BERT
- DeBERTa-v2
- DistilBERT
- MPNet
- ViT
- XLM-RoBERTa
History
View the changelog
Contributing
Everyone is encouraged to help improve this project. Here are a few ways you can help:
- Report bugs
- Fix bugs and submit pull requests
- Write, clarify, or fix documentation
- Suggest or add new features
To get started with development:
git clone https://github.com/ankane/transformers-ruby.git
cd transformers-ruby
bundle install
bundle exec rake download:files
bundle exec rake test