Instructions to use DeepPavlov/t5-wikidata5M-with-neighbors with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepPavlov/t5-wikidata5M-with-neighbors with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="DeepPavlov/t5-wikidata5M-with-neighbors")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("DeepPavlov/t5-wikidata5M-with-neighbors")
model = AutoModelForSeq2SeqLM.from_pretrained("DeepPavlov/t5-wikidata5M-with-neighbors")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DeepPavlov/t5-wikidata5M-with-neighbors with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepPavlov/t5-wikidata5M-with-neighbors"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepPavlov/t5-wikidata5M-with-neighbors",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DeepPavlov/t5-wikidata5M-with-neighbors

SGLang

How to use DeepPavlov/t5-wikidata5M-with-neighbors with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "DeepPavlov/t5-wikidata5M-with-neighbors" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepPavlov/t5-wikidata5M-with-neighbors",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "DeepPavlov/t5-wikidata5M-with-neighbors" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepPavlov/t5-wikidata5M-with-neighbors",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DeepPavlov/t5-wikidata5M-with-neighbors with Docker Model Runner:
```
docker model run hf.co/DeepPavlov/t5-wikidata5M-with-neighbors
```

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

This is a t5-small model trained on the wikidata5M dataset.

This model was trained on tail and entity prediction in a knowledge graph using the graph's context represented by the node's neighborhood.

Textual representation was obtained from wikidata entities and relation titles. Entity description was used to disambiguate if two entities had the same title. If still, no disambiguation was possible, we assigned unique numerical ids for such entities.

The neighborhood for the input was obtained as follows:

sort the neighborhood by semantic similarity of relations from its triplets to the relation from the input triplet in order to prioritize more important information in the context;
limit the sorted neighborhood to 512 triplets, since this will always be at least as big as the size of the allowed context, and, after verbalization, specify the maximum length of 512 for the model tokenizer to fit the resulting verbalized neighborhood representation into the language model context.

Neighborhood sorting by semantic proximity was performed using a pre-calculated matrix of cosine similarity of relations in KG, for similarity calculation the relations were embedded by the fasttext model.

We trained the model on the Wikidata5M dataset for approximately 5M iterations on 8xA100 GPUs using a batch size of 320.

To evaluate the model, we sample 50 times from the decoder for each input and then rank the predictions by their log probabilities. We achieve 0.319 Hits@1 on the test set.

One can load this model for their personal use of fine-tuning as follows:

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("DeepPavlov/t5-wikidata5M-with-neighbors")
model = AutoModelForSeq2SeqLM.from_pretrained("DeepPavlov/t5-wikidata5M-with-neighbors")

Downloads last month: 10