metadata
license: mit
intel-optimized-model-for-embeddings-v1
This is a text embedding model model: It maps sentences & paragraphs to a 512 dimensional dense vector space and can be used for tasks like clustering or semantic search. For sample code that uses this model in a torch serve container see Intel-Optimized-Container-for-Embeddings.
Usage
Install the required packages:
pip install -U torch==2.3.1+cpu --extra-index-url https://download.pytorch.org/whl/cpu
pip install -U transformers==4.42.4 intel-extension-for-pytorch==2.3.100
Use the following example below to load the model with the transformers library, tokenize the text, run the model, and apply pooling to the output.
# example embedding code
import torch
from transformers import AutoTokenizer, AutoModel
import intel_extension_for_pytorch as ipex
# load model
tokenizer = AutoTokenizer.from_pretrained('Intel/intel-optimized-model-for-embeddings-v1')
model = AutoModel.from_pretrained('Intel/intel-optimized-model-for-embeddings-v1', torchscript=True)
model.eval()
# do IPEX optimization
batch_size = 1
seq_length=512
vocab_size = model.config.vocab_size
sample_input = {"input_ids": torch.randint(vocab_size, size=[batch_size, seq_length]),
"token_type_ids": torch.zeros(size=[batch_size, seq_length],
dtype=torch.int),
"attention_mask": torch.randint(1, size=[batch_size, seq_length])}
text = "This is a test."
model = ipex.optimize(model, level="O1",auto_kernel_selection=True,
conv_bn_folding=False, dtype=torch.bfloat16)
with torch.no_grad(), torch.cpu.amp.autocast(cache_enabled=False,
dtype=torch.bfloat16):
# Compile model
model = torch.jit.trace(model, example_kwarg_inputs=sample_input,
check_trace=False, strict=False)
model = torch.jit.freeze(model)
# Call model
tokenized_text = tokenizer(text, padding=True, truncation=True, return_tensors='pt')
model_output = model(**tokenized_text)
# Do mean pooling
token_embeddings = model_output[0]
attention_mask = tokenized_text['attention_mask']
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
output_sum = torch.sum(token_embeddings * input_mask_expanded, 1)
embeddings = output_sum / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
embeddings = [embeddings[0].tolist()]
# Embeddings output
print(embeddings)
Model Details
Model Description
This model was fine-tuned using the sentence-transformers library based on the BERT-Medium_L-8_H-512_A-8 model.
Training Datasets
| Dataset | Description | License |
|---|---|---|
| beir/dbpedia-entity | DBpedia-Entity is a standard test collection for entity search over the DBpedia knowledge base. | CC BY-SA 3.0 license |
| beir/nq | To help spur development in open-domain question answering, the Natural Questions (NQ) corpus has been created, along with a challenge website based on this data. | CC BY-SA 3.0 license |
| beir/scidocs | SciDocs is a new evaluation benchmark consisting of seven document-level tasks ranging from citation prediction, to document classification and recommendation. | GNU General Public License v3.0 license |
| beir/trec-covid | TREC-COVID followed the TREC model for building IR test collections through community evaluations of search systems. | CC-BY-SA-4.0 license |
| beir/touche2020 | Given a question on a controversial topic, retrieve relevant arguments from a focused crawl of online debate portals. | CC BY 4.0 license |
| WikiAnswers | The WikiAnswers corpus contains clusters of questions tagged by WikiAnswers users as paraphrases. | MIT |
| Cohere/wikipedia-22-12-en-embeddings Dataset | The Cohere/Wikipedia dataset is a processed version of the wikipedia-22-12 dataset. It is English only, and the articles are broken up into paragraphs. | Apache 2.0 |
| MLNI | GLUE, the General Language Understanding Evaluation benchmark (https://gluebenchmark.com/) is a collection of resources for training, evaluating, and analyzing natural language understanding systems. | MIT |