{MODEL_NAME}

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

Evaluation Results

For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net

Training

The model was trained with the parameters:

DataLoader:

torch.utils.data.dataloader.DataLoader of length 500 with parameters:

{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss:

gpl.toolkit.loss.MarginDistillationLoss

Parameters of the fit()-Method:

{
    "epochs": 1,
    "evaluation_steps": 0,
    "evaluator": "NoneType",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": 500,
    "warmup_steps": 1000,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 350, 'do_lower_case': False}) with Transformer model: DistilBertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

Citing & Authors

Metadata

Release files for RelevanceAI-dev 2.1.0.2022.4.16.11.3.0.252001

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for RelevanceAI-dev 2.1.0.2022.4.16.11.3.0.252001
File	Size	Uploaded
RelevanceAI-dev-2.1.0.2022.4.16.11.3.0.252001.tar.gz	201.6 kB	Apr 16, 2022	Details

Built distribution (wheel)

Table of built distributions (wheels) for RelevanceAI-dev 2.1.0.2022.4.16.11.3.0.252001
File	Interpreter	ABI	Platform	Reset
RelevanceAI_dev-2.1.0.2022.4.16.11.3.0.252001-py3-none-any.whl 274.5 kB Apr 16, 2022	Python 3	none	any	Details

Total release size: 476.1 kB

Release files / RelevanceAI-dev-2.1.0.2022.4.16.11.3.0.252001.tar.gz

Download URL	RelevanceAI-dev-2.1.0.2022.4.16.11.3.0.252001.tar.gz
Size	201.6 kB
Tags	Source
SHA-256 checksum How to use checksums	`3e1e81251609a5fa1dc7a8dc35520bd9c18bb69a254fcac21de3314bf0f36813`
BLAKE2b-256 checksum How to use checksums	`ef7c86e12e6a9a997cda873d54add28941462fb31addc8f204013c450010ae10`
Upload date	Apr 16, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.0 CPython/3.10.4`

Release files / RelevanceAI_dev-2.1.0.2022.4.16.11.3.0.252001-py3-none-any.whl

Download URL	RelevanceAI_dev-2.1.0.2022.4.16.11.3.0.252001-py3-none-any.whl
Size	274.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`ef38b9d13955103980581d6052a204a29614bec7a95e84b695d0d0e6c759e015`
BLAKE2b-256 checksum How to use checksums	`9afd01d4d4898671e660db707d38b491063db47b1acaade4d1cbf456de964a24`
Upload date	Apr 16, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.0 CPython/3.10.4`