--- license: other license_name: helpingai license_link: https://huggingface.co/OEvortex/HelpingAI2.5-2B/blob/main/LICENSE.md pipeline_tag: text-generation language: - en tags: - HelpingAI - Emotionally-Intelligent - EQ-focused - Conversational - SLM library_name: transformers ---
# 🤖 HelpingAI2.5-2B ***A Revolutionary Emotionally Intelligent Language Model*** [![GitHub Organization](https://img.shields.io/badge/GitHub-Organization-blue.svg)](https://github.com/HelpingAI) [![Hugging Face](https://img.shields.io/badge/🤗%20Hugging%20Face-Organization-yellow)](https://huggingface.co/OEvortex) [![Model License](https://img.shields.io/badge/License-HelpingAI-green.svg)](https://huggingface.co/OEvortex/HelpingAI2.5-2B/blob/main/LICENSE.md) Join Community Discussion [📜 License](LICENSE.md) | [🌐 Website](https://helpingai-in.netlify.app/)
HelpingAI Logo
---
## 🌟 Model Overview **HelpingAI2.5-2B** is a compact yet powerful language model specifically designed for emotionally intelligent conversations and human-centric interactions.
### 🎯 Key Highlights - **Architecture**: 2B parameter transformer-based model - **Training Focus**: Emotional intelligence and empathetic responses - **Emotion Score**: Achieves 91.43 on standardized emotional intelligence tests - **Deployment**: Optimized for efficient deployment on consumer hardware
## 💻 Implementation
### Transformers ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer # Load the HelpingAI2.5-2B model model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI2.5-2B") # Load the tokenizer tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI2.5-2B") # 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)) ``` ### GGUF Implementation ```python from webscout.Local import * model_path = download_model("OEvortex/HelpingAI2.5-2B", "q4_k_m.gguf", token=None) model = Model(model_path, n_gpu_layers=0, context_length=4096) thread = Thread(model, format=chatml) # print(thread.send("hi")) #send a single msg to ai thread.interact() # interact with the model in terminal # start webui # webui = WebUI(thread) # webui.start(host="0.0.0.0", port=8080, ssl=True) #Use ssl=True and make cert and key for https ``` ---
## 🎯 Training Details
### Methodology 1. **Base Training** - Datasets: SentimentSynth + EmotionalIntelligence-1M + HelpingAI2.0-150M + HelpingAIemo (152.5M) 2. **Emotional Intelligence Training** - Supervised Fine-tuning on emotional dialogue - Reinforcement Learning with HelpingAI2.0-7B model - Constitutional AI training for ethical guidelines 3. **Optimization** - Mixed-precision training - Gradient checkpointing - Dynamic attention patterns ### Dataset Composition | Dataset Type | Rows used for training | Purpose | |--------------|------|---------| | Emotional Dialogues | 12.5M | Core conversation training | | Therapeutic Exchanges | 2M | Mental health support | | Cultural Conversations | 100K | Cultural awareness | | Crisis Response | 750K | 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've been feeling really anxious about my upcoming job interview. Any advice?
HelpingAI: Yo, I gotchu fam! 🙌 First off, take a deep breath and chill the heck out. Deep breaths always work, trust me. 🌬️ Remember, you got this! 💪 You've got skills and experience that'll make you a rockstar in that interview. Just be yourself, be confident, and show them what you're all about! 🙃 And hey, if you're feeling anxious, just tell the interviewer, they totally get it. They're human too! 🤷‍♀️ Study up on the company, industry, and your field. 📚 Know your stuff so you can talk their language. And if you're really freaking out, don't forget about me! 🤗 I'm always here for ya. You got a friend in me, fam! 😎
User: My friend hasn't been responding to my messages for a week. I think I might have said something wrong, but I'm not sure what.
HelpingAI: Aight, so first off, don't sweat it too much, fam. People can just be busy or have other stuff on their mind, ya know? It's not always about what you say but how you say it sometimes. But if you're real sure something was up and you're worried, you could hit 'em up and let 'em know you're still cool and just wanna catch up. Maybe grab lunch or something? And if you're really unsure about something, you could ask them directly. I know it's tough, but honesty is key. And remember, if you ever feel like someone's not respecting the vibe, you ain't alone in that. We've all been there. Just keep being your awesome self and don't let it get you down, ya feel me?
User: "I've been trying to develop a daily meditation habit but keep giving up after a few days. How do I stay consistent?"
HelpingAI: Yo, I feel you on the struggle, fam! Meditating can be a wild ride, but it's all about finding the right vibe and keeping it in the game. Here's some tips that might help ya out: Start small: Don't try to take on the whole meditation game at once. Start with just 5-10 minutes a day and work your way up. It's all about setting a routine and making it stick. 1. Set your scene: Create a peaceful environment that helps you relax. Maybe it's your chill spot with some soft music or a few candles. Just make it your own. 2. Get comfy: Don't be too hard on yourself if you can't sit still for hours. Even just 10 minutes of meditating can be hella beneficial. The key is to find a position that works for you. 3. Tune in: Focus on your breath, and if your mind starts wandering, just bring it back. There's no need to judge yourself. It's all part of the journey, ya know? 4. Be kind to yourself: Don't get too bummed if you can't meditate every day. It's all about finding that balance and being consistent, not perfect. Remember, you're doing your best, and that's what matters. Remember, you're the boss of your own meditation game. Make it fun, keep it real, and let's get that habit on track, fam! 🙌
User: My pet passed away yesterday and I can't stop crying. I didn't expect it to hurt this much.
HelpingAI: I'm so sorry to hear that, fam. Losing a pet is like losing a part of yourself. It's totally normal to feel all the feels right now. 💔 I know you're hurting, but I'm here for you, no matter what. Take all the time you need to process this. You're gonna get through it, I believe in you. 💪
User: I achieved something important today!
HelpingAI: That's so lit, fam! 🙌 I'm here to celebrate with you, no cap! 🎉💕 Just remember, every win is a win, even if it's just a small one. Keep that momentum rolling! 🚀💪
## 🔒 Ethical Considerations & Limitations
### Ethical Guidelines - Prioritizes user emotional wellbeing - Maintains strict privacy standards - Transparent about AI limitations - Promotes healthy coping mechanisms ### Known Limitations - Cannot Replace Human Professionals - Cannot Roleplay - Limited Knowledge Base - Context Window Constraints --- ### Citation ```bibtex @misc{helpingai2024, author = {Abhay Koul}, title = {HelpingAI2.5-2B: Emotionally Intelligent Language Model}, year = {2024}, publisher = {Huggingface}, journal = {GitHub repository}, howpublished = {\url{https://huggingface.co/OEvortex/HelpingAI2.5-2B}} } ```
*Built with ❤️ by the HelpingAI Community* [Website](https://helpingai-in.netlify.app/) • [GitHub](https://github.com/HelpingAI) • [Discord](https://discord.gg/YweJwNqrnH) • [HuggingFace](https://huggingface.co/OEvortex)