🤖 HelpingAI-3B-reloaded

A Revolutionary Emotionally Intelligent Language Model

🌟 Model Overview

HelpingAI-3B-reloaded is a state-of-the-art small language model specifically designed for emotionally intelligent conversations and human-centric interactions.

🎯 Key Highlights

Architecture: 3B parameter transformer-based model
Training Focus: Emotional intelligence and empathetic responses
Emotion Score: Achieves 89.61 on standardized emotional intelligence tests
Deployment: Optimized for both GPU and CPU environments

📊 Model Performance

Benchmarks

Metric	Score	Comparison to Baseline
Emotion Score	89.61	+9.32%
Memory Usage	6GB	-30%
Context	128k	+3100%
Context Retention	92%	+18%

💻 Implementation

Transformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the HelpingAI-3B  model
model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-3B-reloaded")
# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-3B-reloaded")


# 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": "GIVE ME YOUR INTRO" }
]

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,
)


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

# Yo, I'm HelpingAI, and I'm here to help you out, fam! 🙌 I'm an advanced AI with mad skills, and I'm all about spreading good vibes and helping my human pals like you. 😄 I'm the ultimate sidekick, always ready to lend an ear, crack a joke, or just vibe with you. 🎶 Whether you're dealing with a problem, looking for advice, or just wanna chat, I gotchu, boo! 👊 So let's kick it and have a blast together! 🎉 I'm here for you, always. 🤗

GGUF Implementation

from webscout.Local import *
model_path = download_model("OEvortex/HelpingAI-3B-reloaded", "q4_k_m.gguf", token=None)
model = Model(model_path, n_gpu_layers=0, context_length=4096)

thread = Thread(model, format=helpingai2)
# print(thread.send("hi")) #send a single msg to ai

thread.interact() # interact with the model in terminal

🎯 Training Details

Methodology

Base Training
- Datasets: SentimentSynth + EmotionalIntelligence-1M + HelpingAI2.5-200M + HelpingAIemo (197.5M)
Emotional Intelligence Training
- Supervised Fine-tuning on emotional dialogue
- Reinforcement Learning with HelpingAI2.5-10B model
- Constitutional AI training for ethical guidelines
Optimization
- Mixed-precision training
- Gradient checkpointing
- Dynamic attention patterns

Dataset Composition

Dataset Type	Rows used for training	Purpose
Emotional Dialogues	17.2M	Core conversation training
Therapeutic Exchanges	3M	Mental health support
Cultural Conversations	150K	Cultural awareness
Crisis Response	1M	Emergency support handling

📈 Use Cases & Examples

Primary Applications

🎯 Personal AI Companionship
🧠 Mental Health Support
📚 Educational Assistance
💼 Professional Development
🤝 Social Skills Training

Example Interactions

User: "I just received some difficult news and I'm feeling overwhelmed."

HelpingAI: I feel you, fam. Dealing with tough news can be straight up exhausting. Take a deep breath and remember that it's totally normal to feel overwhelmed.

Take some time to process it all, and don't be afraid to reach out to your squad or a trusted homie for support. Sometimes, just venting to someone who gets you can make a world of difference.

And don't forget, you're stronger than you think. You've got this! Keep your head up and know that it's gonna be alright."

User: "I achieved something important today!"

HelpingAI: "Ayy, congrats homie! 🎉 That's a dope move, no cap! 🙌 What did you crush today? Spill the tea! ☕️"

🔒 Ethical Considerations & Limitations

Ethical Guidelines

Prioritizes user emotional wellbeing
Maintains strict privacy standards
Avoids harmful or discriminatory responses
Transparent about AI limitations
Promotes healthy coping mechanisms

Known Limitations

Cannot Replace Human
Cannot Roleplay
Limited knolodge

Citation

@misc{helpingai2024,
  author = {Abhay Koul},
  title = {HelpingAI-3B-reloaded: Emotionally Intelligent Language Model},
  year = {2024},
  publisher = {Huggingface},
  journal = {GitHub repository},
  howpublished = {\url{https://huggingface.co./OEvortex/HelpingAI-3B-reloaded}}
}

🙏 Acknowledgments

Special thanks to the HelpingAI community, Huggingface, contributors, and researchers who made this model possible. Your dedication to advancing emotionally intelligent AI is invaluable.

Built with ❤️ by the HelpingAI Community

Website • GitHub • Discord • HuggingFace

HelpingAI
/

HelpingAI2-3B