# Hugging Face Inference Endpoints -compatible version of michaelfeil/ct2fast-e5-small-v2

Duplicate of michaelfeil/ct2fast-e5-small-v2, modified to run on Hugging Face Inference Endpoints.

Requires a GPU Instance type to run. Creates symbolic links so that ctranslate2 reads the repository model without downloading from HF.

# Fast-Inference with Ctranslate2

Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.

quantized version of intfloat/e5-small-v2

pip install hf-hub-ctranslate2>=2.12.0 ctranslate2>=3.16.0
# from transformers import AutoTokenizer
model_name = "michaelfeil/ct2fast-e5-small-v2"
model_name_orig="intfloat/e5-small-v2"

from hf_hub_ctranslate2 import EncoderCT2fromHfHub
model = EncoderCT2fromHfHub(
        # load in int8 on CUDA
        model_name_or_path=model_name,
        device="cuda",
        compute_type="int8_float16"
)
outputs = model.generate(
    text=["I like soccer", "I like tennis", "The eiffel tower is in Paris"]
) # perform downstream tasks on outputs
outputs["pooler_output"]
outputs["last_hidden_state"]
outputs["attention_mask"]

# alternative, use SentenceTransformer Mix-In
# for end-to-end Sentence embeddings generation
# (not pulling from this CT2fast-HF repo)

from hf_hub_ctranslate2 import CT2SentenceTransformer
model = CT2SentenceTransformer(
    model_name_orig, compute_type="int8_float16", device="cuda"
)
embeddings = model.encode(
    ["I like soccer", "I like tennis", "The eiffel tower is in Paris"],
    batch_size=32,
    convert_to_numpy=True,
    normalize_embeddings=True,
)
print(embeddings.shape, embeddings)
scores = (embeddings @ embeddings.T) * 100

Checkpoint compatible to ctranslate2>=3.16.0 and hf-hub-ctranslate2>=2.12.0

  • compute_type=int8_float16 for device="cuda"
  • compute_type=int8 for device="cpu"

Converted on 2023-06-19 using

ct2-transformers-converter --model intfloat/e5-small-v2 --output_dir ~/tmp-ct2fast-e5-small-v2 --force --copy_files tokenizer.json modules.json README.md tokenizer_config.json sentence_bert_config.json vocab.txt special_tokens_map.json .gitattributes --trust_remote_code

Licence and other remarks:

This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.

Original description

E5-small-v2

Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022

This model has 12 layers and the embedding size is 384.

Usage

Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset.

import torch.nn.functional as F

from torch import Tensor
from transformers import AutoTokenizer, AutoModel


def average_pool(last_hidden_states: Tensor,
                 attention_mask: Tensor) -> Tensor:
    last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]


# Each input text should start with "query: " or "passage: ".
# For tasks other than retrieval, you can simply use the "query: " prefix.
input_texts = ['query: how much protein should a female eat',
               'query: summit define',
               "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
               "passage: Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."]

tokenizer = AutoTokenizer.from_pretrained('intfloat/e5-small-v2')
model = AutoModel.from_pretrained('intfloat/e5-small-v2')

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])

# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())

Training Details

Please refer to our paper at https://arxiv.org/pdf/2212.03533.pdf.

Benchmark Evaluation

Check out unilm/e5 to reproduce evaluation results on the BEIR and MTEB benchmark.

Citation

If you find our paper or models helpful, please consider cite as follows:

@article{wang2022text,
  title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2212.03533},
  year={2022}
}

Limitations

This model only works for English texts. Long texts will be truncated to at most 512 tokens.

Sentence Transformers

Below is an example for usage with sentence_transformers. pip install sentence_transformers~=2.2.2 This is community contributed, and results may vary up to numerical precision.

from sentence_transformers import SentenceTransformer
model = SentenceTransformer('intfloat/e5-small-v2')
embeddings = model.encode(input_texts, normalize_embeddings=True)
Downloads last month
15
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Spaces using anttip/ct2fast-e5-small-v2-hfie 4

Evaluation results