Instructions to use OEvortex/Wise-EMO-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OEvortex/Wise-EMO-2B with Transformers:

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

pipe = pipeline("text-generation", model="OEvortex/Wise-EMO-2B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OEvortex/Wise-EMO-2B")
model = AutoModelForCausalLM.from_pretrained("OEvortex/Wise-EMO-2B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OEvortex/Wise-EMO-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OEvortex/Wise-EMO-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OEvortex/Wise-EMO-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OEvortex/Wise-EMO-2B

SGLang

How to use OEvortex/Wise-EMO-2B 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 "OEvortex/Wise-EMO-2B" \
    --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": "OEvortex/Wise-EMO-2B",
		"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 "OEvortex/Wise-EMO-2B" \
        --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": "OEvortex/Wise-EMO-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OEvortex/Wise-EMO-2B with Docker Model Runner:
```
docker model run hf.co/OEvortex/Wise-EMO-2B
```

Wise-EMO-2B

Overview

Wise-EMO-2B is a 2.5 billion parameter conversational AI model that combines emotional intelligence capabilities from the EMO-2B model with insights from ancient Indian wisdom traditions. By integrating the wealth of knowledge from philosophies like Yoga, Vedanta, Buddhism, Jainism, Sikhism, Hinduism, and other indigenous spiritual practices, this model aims to provide emotionally resonant dialogue infused with profound philosophical perspectives.

Key Features

Emotional Intelligence: Inherited from EMO-2B, Wise-EMO-2B excels at perceiving and responding to emotional undertones with empathy, providing emotionally supportive responses.
Philosophical Wisdom: The model has been further finetuned on texts from ancient Indian wisdom traditions, allowing it to draw upon profound philosophical concepts when appropriate.
Holistic Perspective: Wise-EMO-2B offers a holistic viewpoint that combines emotional resonance with spiritual and philosophical wisdom for a well-rounded, insightful conversational experience.
Dynamic Contextualization: The model adapts its communication style, emotional responses, and philosophical framing based on the specific conversational context.

Use Cases

Wise-EMO-2B can be beneficial for applications that require emotionally intelligent yet philosophically grounded dialogue, such as:

Emotional support companions with a wisdom-oriented perspective
Philosophical discussion and ideation
Storytelling and creative writing with profound themes
Personal growth, self-reflection, and mindfulness practice
Exploring ancient wisdom in relation to modern issues

Limitations and Responsible Use

While powerful, Wise-EMO-2B is an AI model with inherent limitations. Its responses should be viewed as a supportive tool rather than a substitute for professional mental health services or spiritual guidance. Additionally, the model may reflect biases from its training data. Users should think critically and report concerning outputs.

As with all AI systems, Wise-EMO-2B should be used responsibly and ethically, particularly given the sensitivity around philosophy and spiritual beliefs. Outputs should be carefully evaluated in context.

This is mark one of Wise-EMO, It is just for testing purposes

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

F16

Dataset used to train OEvortex/Wise-EMO-2B

Space using OEvortex/Wise-EMO-2B 1

Collection including OEvortex/Wise-EMO-2B

Emotional Intelligence

Collection

Models are listed based on EQ • 17 items • Updated Oct 6, 2024 • 9