OEvortex/HelpingAI-3B-v2.1

HelpingAI-3B-v2: Emotionally Intelligent Conversational AI

Introduction

HelpingAI-3B-v2 is a state-of-the-art large language model specializing in emotionally intelligent conversation. With advanced emotional understanding capabilities, it can engage in empathetic dialogue tailored to the user's emotional state and context.

Emotional Intelligence Capabilities

HelpingAI-3B-v2 exhibits several key traits that enable emotionally resonant responses:

• Emotion recognition and validation
• Empathetic perspective-taking
• Generating emotionally supportive language
• Contextual emotional attunement
• Using appropriate tone, word choice and emotional expression

Whether comforting someone grieving, celebrating positive news, or addressing complex feelings, HelpingAI-3B-v2 can adapt its communication style with emotional nuance.

Examples of Emotionally Intelligent Responses

"Oh no! 😔 Dealing with printer issues can be frustrating. Let's try to help you get it up and running. First, make sure the printer is properly connected to the power source and your computer. Check if there are any error messages or blinking lights on the printer. It's also a good idea to restart both the printer and your computer. If the issue persists, you may need to reinstall the printer drivers or check for any hardware issues. Let me know if you need more help! "

"It's really sad to hear about your friend's loss. 😔 Losing a parent can be incredibly painful and heart-wrenching. It's important to show them empathy and support during this difficult time. You Offer to be there for them and listen to them when they're ready to talk. You Send them thoughtful and comforting messages to let them know that you are thinking of them and that they are not alone. Offer to help them with any practical tasks or duties they might have, like running errands or taking care of animals. Remember, everyone experiences grief differently, so it's essential to be patient and understanding. Offer your friend a hug if they're comfortable with it, and remind them that you are there for them. 🌼"

The model tailors its language, tone and emotional content to be contextually appropriate, combining emotional intelligence with factual knowledge and practical suggestions.

Performance Comparison

The performance of HelpingAI-3B-v2 is compared with other relevant models on various metrics in the table below:

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
HelpingAI-3B-v2	57.44	53.14	82.61	47.42	57.92	68.15	35.39
rocket-3B	55.77	50.6	76.69	47.1	55.82	67.96	36.47
HelpingAI-3B	55.59	50.6	76.64	46.82	55.62	67.8	36.09
stableLM-zephyr-3b	53.43	46.08	74.16	46.17	46.49	65.51	42.15
mmd-3b	53.22	44.8	70.41	50.9	43.2	66.22	43.82
MiniGPT-3B-Bacchus	52.55	43.52	70.45	50.49	43.52	66.85	40.49
MiniGPT-3B-Hercules-v2.0	52.52	43.26	71.11	51.82	40.37	66.46	42.08
MiniGPT-3B-OpenHermes-2.5-v2	51.91	47.44	72	53.06	42.28	65.43	31.24
MiniChat-2-3B	51.49	44.88	67.69	47.59	49.64	66.46	32.68
smol-3b	50.27	46.33	68.23	46.33	50.73	65.35	24.64
MiniChat-1.5-3B	50.23	46.5	68.28	46.67	50.71	65.04	24.18
3BigReasonCinder	48.16	41.72	65.16	44.79	44.76	64.96	27.6
MintMerlin-3B	47.63	44.37	66.56	43.21	47.07	64.4	20.17

Simple Usage Code

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

# Let's bring in the big guns! Our super cool HelpingAI-3B model
model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-3B-v2", trust_remote_code=True, torch_dtype=torch.float16).to("cuda")

# We also need the special HelpingAI translator to understand our chats
tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-3B-v2", trust_remote_code=True, torch_dtype=torch.float16)

# This TextStreamer thingy is our secret weapon for super smooth conversation flow
streamer = TextStreamer(tokenizer)

# Now, here comes the magic! ✨ This is the basic template for our chat
prompt = """
<|im_start|>system: {system}
<|im_end|>
<|im_start|>user: {insaan}
<|im_end|>
<|im_start|>assistant:
"""

# Okay, enough chit-chat, let's get down to business!  Here's what our system will be our system prompt
# We recommend to Use HelpingAI style in system prompt as this model is just trained on 1K rows of fealings dataset and we are working on even better model
system = "You are HelpingAI a emotional AI always answer my question in HelpingAI style"


# And the insaan is curious (like you!) insaan means human in hindi
insaan = "My best friend recently lost their parent to cancer after a long battle. They are understandably devastated and struggling with grief. What would be a caring and supportive way to respond to help them through this difficult time?"

# Now we combine system and user messages into the template, like adding sprinkles to our conversation cupcake
prompt = prompt.format(system=system, insaan=insaan)

# Time to chat! We'll use the tokenizer to translate our text into a language the model understands
inputs = tokenizer(prompt, return_tensors="pt", return_attention_mask=False).to("cuda")

# Here comes the fun part!  Let's unleash the power of HelpingAI-3B to generate some awesome text
generated_text = model.generate(**inputs, max_length=3084, top_p=0.95, do_sample=True, temperature=0.6, use_cache=True, streamer=streamer)