Instructions to use HelpingAI/HelpingAI2-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use HelpingAI/HelpingAI2-3B with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HelpingAI/HelpingAI2-3B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf HelpingAI/HelpingAI2-3B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HelpingAI/HelpingAI2-3B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf HelpingAI/HelpingAI2-3B:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf HelpingAI/HelpingAI2-3B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf HelpingAI/HelpingAI2-3B:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf HelpingAI/HelpingAI2-3B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HelpingAI/HelpingAI2-3B:Q4_K_M

Use Docker

docker model run hf.co/HelpingAI/HelpingAI2-3B:Q4_K_M

LM Studio
Jan

vLLM

How to use HelpingAI/HelpingAI2-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HelpingAI/HelpingAI2-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HelpingAI/HelpingAI2-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HelpingAI/HelpingAI2-3B:Q4_K_M

Ollama
How to use HelpingAI/HelpingAI2-3B with Ollama:
```
ollama run hf.co/HelpingAI/HelpingAI2-3B:Q4_K_M
```

Unsloth Studio

How to use HelpingAI/HelpingAI2-3B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for HelpingAI/HelpingAI2-3B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for HelpingAI/HelpingAI2-3B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HelpingAI/HelpingAI2-3B to start chatting

How to use HelpingAI/HelpingAI2-3B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HelpingAI/HelpingAI2-3B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "HelpingAI/HelpingAI2-3B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use HelpingAI/HelpingAI2-3B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HelpingAI/HelpingAI2-3B:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default HelpingAI/HelpingAI2-3B:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use HelpingAI/HelpingAI2-3B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HelpingAI/HelpingAI2-3B:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "HelpingAI/HelpingAI2-3B:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use HelpingAI/HelpingAI2-3B with Docker Model Runner:
```
docker model run hf.co/HelpingAI/HelpingAI2-3B:Q4_K_M
```

Lemonade

How to use HelpingAI/HelpingAI2-3B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HelpingAI/HelpingAI2-3B:Q4_K_M

Run and chat with the model

lemonade run user.HelpingAI2-3B-Q4_K_M

List all available models

lemonade list

HelpingAI2-3B / README.md

Abhaykoul

Update README.md

aaee653 verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

7.1 kB

	---
	license: other
	license_name: helpingai
	license_link: https://huggingface.co/OEvortex/HelpingAI-3B-v3/blob/main/LICENSE.md
	pipeline_tag: text-generation
	language:
	- en
	tags:
	- HelpingAI
	- Emotionally-Intelligent
	- EQ-focused- EQ-focused
	- Conversational
	- SLM

	---

	<div align="center">

	# 🤖 HelpingAI-3B-reloaded

	*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/HelpingAI-3B-v3/blob/main/LICENSE.md)


	<a href="https://github.com/HelpingAI/community/discussions">
	<img src="https://img.shields.io/badge/Join-Community%20Discussion-blue?style=for-the-badge&logo=github" alt="Join Community Discussion">
	</a>

	[📜 License](LICENSE) \| [🌐 Website](https://helpingai-in.netlify.app/)

	</div>

	<div align="center">
	<img src="https://huggingface.co/OEvortex/HelpingAI-3B/resolve/main/HelpingAI.png" alt="HelpingAI Logo" width="300px">
	</div>

	---

	<div align="center">

	## 🌟 Model Overview

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

	</div>

	### 🎯 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


	---

	<div align="center">

	## 📊 Model Performance

	</div>

	### Benchmarks

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


	---

	<div align="center">

	## 💻 Implementation

	</div>

	### Transformers

	```python
	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

	```python
	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

	```

	---

	<div align="center">

	## 🎯 Training Details

	</div>

	### Methodology

	1. Base Training
	- Datasets: SentimentSynth + EmotionalIntelligence-1M + HelpingAI2.5-200M + HelpingAIemo (197.5M)

	2. Emotional Intelligence Training
	- Supervised Fine-tuning on emotional dialogue
	- Reinforcement Learning with HelpingAI2.5-10B 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 \| 17.2M \| Core conversation training \|
	\| Therapeutic Exchanges \| 3M \| Mental health support \|
	\| Cultural Conversations \| 150K \| Cultural awareness \|
	\| Crisis Response \| 1M \| Emergency support handling \|

	---

	<div align="center">

	## 📈 Use Cases & Examples

	</div>

	### Primary Applications

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

	### Example Interactions

	<div style="background-color: #f5f5f5; padding: 15px; border-radius: 5px; margin: 10px 0;">

	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."

	</div>

	<div style="background-color: #f5f5f5; padding: 15px; border-radius: 5px; margin: 10px 0;">

	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! ☕️"

	</div>

	---

	<div align="center">

	## 🔒 Ethical Considerations & Limitations

	</div>

	### 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

	```bibtex
	@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}}
	}
	```

	---

	<div align="center">

	## 🙏 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.

	</div>

	---

	<div align="center">

	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)

	</div>