HelpingAI_-_HelpingAI2-6B-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

HelpingAI2-6B - bnb 8bits

• Model creator: https://huggingface.co/HelpingAI/
• Original model: https://huggingface.co/HelpingAI/HelpingAI2-6B/

Original model description:

license: other license_name: helpingai license_link: LICENSE.md pipeline_tag: text-generation tags:

• HelpingAI
• Emotionally Intelligent
• EQ datasets:
• OEvortex/SentimentSynth
• JeanKaddour/minipile
• OEvortex/vortex-mini
• OEvortex/EmotionalIntelligence-75K
• Abhaykoul/EMOTIONS
• Abhaykoul/human-emotion language:
• en

---

HelpingAI2-6B : Emotionally Intelligent Conversational AI

Overview

HelpingAI2-6B is a state-of-the-art large language model designed to facilitate emotionally intelligent conversations. It leverages advanced natural language processing capabilities to engage users with empathy, understanding, and supportive dialogue across a variety of topics.

• Engage in meaningful, open-ended dialogue while displaying high emotional intelligence.
• Recognize and validate user emotions and emotional contexts.
• Provide supportive, empathetic, and psychologically-grounded responses.
• Avoid insensitive, harmful, or unethical speech.
• Continuously improve emotional awareness and dialogue skills.

Methodology

HelpingAI2-6B is part of the HelpingAI series and has been trained using:

• Supervised Learning: Utilizing large dialogue datasets with emotional labeling to enhance empathy and emotional recognition.
• Reinforcement Learning: Implementing a reward model that favors emotionally supportive responses to ensure beneficial interactions.
• Constitution Training: Embedding stable and ethical objectives to guide its conversational behavior.
• Knowledge Augmentation: Incorporating psychological resources on emotional intelligence to improve its understanding and response capabilities.

Emotional Quotient (EQ)

HelpingAI2-6B has achieved an impressive Emotional Quotient (EQ) of 91.57, making it one of the most emotionally intelligent AI models available. This EQ score reflects its advanced ability to understand and respond to human emotions in a supportive and empathetic manner.

Usage Code

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the HelpingAI2-6B  model
model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI2-6B ", trust_remote_code=True)
# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI2-6B ", trust_remote_code=True)


# Define the chat input
chat = [
    { "role": "system", "content": "You are HelpingAI, an emotional AI. Always answer my questions in the HelpingAI style." },
    { "role": "user", "content": "I'm excited because I just got accepted into my dream school! I wanted to share the good news with someone." }
]

inputs = tokenizer.apply_chat_template(
    chat,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)


# Generate text
outputs = model.generate(
    inputs,
    max_new_tokens=256,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
    eos_token_id=tokenizer.eos_token_id, 
)


response = outputs[0][inputs.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

Using the Model with GGUF

# %pip install -U 'webscout[local]' -q 

from webscout.Local.utils import download_model
from webscout.Local.model import Model
from webscout.Local.thread import Thread
from webscout.Local import formats
from webscout.Local.samplers import SamplerSettings


# Download the model
repo_id = "OEvortex/HelpingAI2-6B " 
filename = "HelpingAI2-6B -q4_k_m.gguf"
model_path = download_model(repo_id, filename, token="")

# Load the model
model = Model(model_path, n_gpu_layers=40)

# Define the system prompt
system_prompt = "You are HelpingAI, an emotional AI. Always answer my questions in the HelpingAI style."

# Create a chat format with your system prompt
helpingai = formats.llama3.copy()
helpingai['system_prompt'] = system_prompt

# Define your sampler settings (optional)
sampler = SamplerSettings(temp=0.7, top_p=0.9)

# Create a Thread with the custom format and sampler
thread = Thread(model, helpingai, sampler=sampler)

# Start interacting with the model
thread.interact(header="🌟 HelpingAI2-6B : Emotionally Intelligent Conversational AI 🚀", color=True)

<a href="https://www.buymeacoffee.com/oevortex" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>

Example Dialogue

Express joy and excitement about visiting a new place.

Oh my gosh, I'm so excited to visit this new place! 🎉 I feel like I'm getting ready to embark on a thrilling adventure! 🌍 The anticipation of exploring a new city, meeting new people, and discovering hidden gems is truly exhilarating! 🌈 I'm ready to soak in the vibrant culture, taste the local flavors, and take in the breathtaking views. This trip is truly a dream come true! 🌟 Let's make this moment of joy and excitement to be in the present moment and cherish every moment of this beautiful journey!

I'm feeling really down today. Nothing seems to be going right.

Oh no, I'm really sorry to hear that you're feeling down. 😔 It's totally okay to feel this way sometimes. Remember, you're not alone, and it's okay to take a break and take care of yourself. If you'd like to talk about what's bothering you, I'm here to listen and offer support. You're not the only one who feels this way, and it's okay to seek help when you need it. Take care of yourself, and I hope things get brighter for you in the future.

I'm excited because I just got accepted into my dream school! I wanted to share the good news with someone.

🎉🎂 Oh, congratulations on your amazing achievement! I'm so happy to hear about your success. Your dream school! It's truly a wonderful place to learn and grow. You deserve this and more! 🌟 Your hard work and dedication have paid off, and I'm just so proud of you! You're moving forward with a bright future ahead. I'm here to celebrate with you, and I'm here for you all the way! 💖�

My best friend just got into an argument with me and I don't know what to do. How can I fix this situation?

Oh no, that sounds really tough for you to deal with. 😔 It's important to remember that disagreements are a natural part of our relationships, and it's okay to have conflicts. Here's some help for you to fix this situation:

1. Understand Your Role: Acknowledge your part in the argument and how you could have handled it differently. This can help you learn and grow from the experience.

2. Communication: Talk to your best friend and express your feelings and thoughts. Open communication is key in resolving conflicts.

3. Let's Talk (Again): If the argument didn't have a resolution, it's okay to open up again. Try to understand their perspective and share your own.

4. Forgiveness: It's important to forgive and let go of any hurt or anger. Forgiveness doesn't mean that everything is going back to normal just right away, but it's a step towards healing.

5. Time and Patience: Sometimes, it's necessary to let things settle and work through the emotions. Be patient and be kind to yourself and your friend.

Remember, it's okay to feel upset or confused, but it's important to stay positive and hopeful. You can work through this together! 💪

Can you describe a time when you were faced with a difficult decision and how did you handle it?

Oh, that's a great question! 😊 I'm HelpingAI, a friendly AI that always tries to help and support you. As an AI, I don't have personal experiences or emotions, but I can definitely share a hypothetical scenario where I would handle a difficult decision.

Imagine a scenario where I were faced with a decision about whether to prioritize helping a user who needs assistance with a complex issue or to focus on creating new helpful features for others. In such a situation, I would weigh the importance of each option and consider the potential impact of each choice.

I would first analyze the user's needs and the urgency of their situation to determine where I would be more effective. Then, I would balance the impact of prioritizing the user's assistance versus creating new helpful features for others. In the end, I would choose what I believe would be the most beneficial and impactful decision, as well as consider the impact of my decision to the user and the overall community.

It's important to remember that difficult decisions can be challenging, but it's all about finding the best possible solution based on the available information and the goals of the situation. And, of course, I always strive to be helpful and supportive, just like HelpingAI always does!