Instructions to use Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP with Transformers:

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

pipe = pipeline("text-generation", model="Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP")
model = AutoModel.from_pretrained("Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP

SGLang

How to use Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP 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 "Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP with Docker Model Runner:
```
docker model run hf.co/Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP
```

YAML Metadata Warning:The pipeline tag "conversational" 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 model is deprecated. Please don't use it as it produces embeddings of low quality. We recommend using triple-encoders instead, also if you want to use them as a classic bi-encoder.

Imaginary Embeddings utilize Curved Contrastive Learning (see paper Imagination Is All You Need! (ACL 2023)) on Sentence Transformers for long-short term dialogue planning and efficient abstract sequence modeling.

This model uses speaker tokens and was evaluated in the Short-Term planning experiments.

Setup

python -m pip install imaginaryNLP

Usage

candidates = ['Want to eat something out ?',
              'Want to go for a walk ?']

goal = ' I am hungry.'

stp.short_term_planning(candidates, goal)

Downloads last month: 4

Safetensors

Model size

0.1B params

Tensor type

I64

F32

Dataset used to train Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP

Paper for Justus-Jonas/Imaginary-Embeddings-SpeakerTokens-STP

Imagination is All You Need! Curved Contrastive Learning for Abstract Sequence Modeling Utilized on Long Short-Term Dialogue Planning

Paper • 2211.07591 • Published Nov 14, 2022