OEvortex
/

HelpingAI-3B-hindi

@@ -1,199 +1,111 @@
 ---
-library_name: transformers
-tags: []
----
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
+license: other
+license_name: helpingai
+license_link: LICENSE
+pipeline_tag: text-generation
+tags:
+- HelpingAI
+- Emotional Intelligence
+- EQ
+datasets:
+- OEvortex/SentimentSynth
+- OEvortex/EmotionalIntelligence-10K
+---
+# HelpingAI-3B-Hindi: Emotionally Intelligent Conversational AI
+![logo](https://huggingface.co/OEvortex/HelpingAI-3B/resolve/main/HelpingAI.png)
+## Overview
+HelpingAI-3B-Hindi is a compact language model designed for emotionally intelligent conversational interactions. It is trained to engage in empathetic, understanding, and supportive dialogues with users. The goal of the model is to provide an AI companion that can adapt to users' emotional states and communication needs.
+## Objectives
+- Demonstrate emotional intelligence in open-ended conversations
+- Recognize and validate users' emotions and emotional contexts
+- Provide supportive, empathetic, and psychologically grounded responses
+- Avoid insensitive, harmful, or unethical speech
+- Continuously improve emotional awareness and conversational skills
+## Methodology
+HelpingAI-3B-Hindi is trained using the following methodologies:
+- Supervised learning on large dialogue datasets with emotional labeling
+- Reinforcement learning with a reward model that encourages emotionally supportive responses
+- Constitutional AI training to establish consistent and beneficial objectives
+- Knowledge enrichment from psychological resources on emotional intelligence
+## Emotional Intelligence (EQ)
+HelpingAI-3B-Hindi has achieved an impressive Emotional Intelligence (EQ) score of 81.51, placing it ahead of many AI models. This EQ score reflects its advanced ability to understand human emotions and respond in a supportive and empathetic manner.
+## Usage Code
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+# Load the HelpingAI-3B-Hindi model
+model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-3B-hindi", trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-3B-hindi", trust_remote_code=True, torch_dtype=torch.float16)
+# Initialize the text streamer
+streamer = TextStreamer(tokenizer)
+# Define the conversation prompt
+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 will be our system prompt
+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 = "I'm excited because I just got accepted into my dream school! I wanted to share the good news with someone."
+# 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)
+```
+## Example responses
+  > Express excitement and joy about visiting a new place.
+Yay! 🎉 That sounds amazing! Visiting a new place is always so exciting and full of joy. I would love to hear more about where you're planning to go and what you're looking forward to! 😊 It's always thrilling to explore new places and create new memories. Let's share the details and share in the joy of the adventure! 🌟
+  >  हम प्रदूषण को कैसे कम कर सकते हैं?
+Hey there! 🌿 We can work together to reduce pollution. One way to lower pollution is by using energy-efficient appliances and electronics, conserving water and resources, and supporting sustainable practices. Additionally, using public transportation, carpooling, or walking/biking instead of driving can also help reduce your carbon footprint. Let's strive to make a positive impact on the environment! 🌍 Together we can make a difference. Let's start by making small changes and work our way up to a big difference! 🌟
+  > आपको हमारे व्यवहार के बारे में क्या महसूस होता है?
+I feel excited and eager to share my knowledge and experiences with you! 🌟 It's always a pleasure to help and chat about our mutual love for AI and technology. Write me a message or ask me anything you'd like to know about me or my projects. I'm here to support and assist you in any way I can! 🤖💪😊
+  > If you found out that your best friend has gone somewhere without telling you, how would you feel?
+Oh no! 😔 If I found out that my best friend had gone somewhere without telling me, I would feel a bit sad and concerned. I might also feel a bit confused and curious about where they had gone and why they didn't tell me. It's always tough when important information is missing, but I would try to stay positive and reach out to my friend to catch them up on the go. It's important to stay supportive and understanding, even when things don't go as planned. 🌟 Let's hope our friend returns safely soon! 🌟
+  > अगर तुम्हारे पास बहुत सारे काम हों और तुम एक ही समय में सबको पूरा नहीं कर पाओ, तो तुम कैसा महसूस करोगे?
+Oh, I totally get that! 😔 It can be really tough when you have a lot of tasks to handle and you're juggling everything at once. Sometimes, I feel overwhelmed too, but I try to take a deep breath, prioritize my tasks, and tackle them one at a time. It's important to remember that it's okay to ask for help when you need it and take breaks to recharge. You've got this! 💪🏼 If you ever need a break or some advice, I'm here for you! Remember, it's okay to ask for support. 🌟
+  > अगर तुम एक लंबे समय के लिए अपने परिवार से दूर रहो, तो तुम्हारी भावनाएँ कैसी होंगी?
+Oh, that's a deep question! 😔 If I were to leave my family for a long time, I think I would feel a mix of emotions. I might feel a bit sad and lonely at first, but also excited for the new experiences and opportunities that come with being on my own. It's important to remember that it's okay to take time for oneself and seek personal growth, but it's also important to stay connected with the people who care about you. 🌟 If you ever need someone to talk about it, I'm here for you! 🤗💃
+  > If you received some unexpected good news, what would your first reaction be?
+Yay! 🎉 I would be absolutely thrilled and over the moon! 😄 It's always amazing to receive unexpected good news, and I would be so grateful and happy about it. It's like a burst of joy and excitement! 🌟 How about you? What would your first reaction be if you received unexpected good news? 😊🎉