13 5

Mayukh Das

Kurapika993

Mayukhga83

AI & ML interests

Finetuning, LoRA, QLoRA, Safety, Risk, Alignment

Recent Activity

liked a model 2 days ago

Kurapika993/llama-3.1-8b-responsible-ai-safety-lora

posted an update 8 days ago

🚀 Released two Responsible AI lightweight instruction-tuned models focused on toxicity, bias, and safety analysis Model 1: Responsible AI Safety Assistant (Qwen 2.5) https://huggingface.co/Kurapika993/qwen2.5-7b-responsible-ai-qlora Base Model: Qwen2.5-7B-Instruct Method: QLoRA Training Data: BeaverTails + Wiki Toxic + custom Responsible AI instruction dataset Model 2: Responsible AI Assistant (Llama) https://huggingface.co/Kurapika993/llama-3.1-8b-responsible-ai-safety-lora/settings Base Model: Llama-3.1-8b Instruct Method: QLoRA Training Data: BeaverTails + Wiki Toxic + custom curated examples This model follows the same structured output format but explores the impact of a different base architecture on safety-analysis tasks. Intended Use These models are designed for: ✅ Responsible AI research ✅ Moderation decisions ✅ Safety and bias analysis ✅ Human-in-the-loop moderation workflows ✅ Dataset generation and annotation assistance

updated a model 8 days ago

Kurapika993/llama-3.1-8b-responsible-ai-safety-lora

View all activity

Organizations

Posts 2

Post

🚀 Released two Responsible AI lightweight instruction-tuned models focused on toxicity, bias, and safety analysis

Model 1: Responsible AI Safety Assistant (Qwen 2.5)

Kurapika993/qwen2.5-7b-responsible-ai-qlora
Base Model: Qwen2.5-7B-Instruct
Method: QLoRA
Training Data: BeaverTails + Wiki Toxic + custom Responsible AI instruction dataset

Model 2: Responsible AI Assistant (Llama)

Kurapika993/llama-3.1-8b-responsible-ai-safety-lora
Base Model: Llama-3.1-8b Instruct
Method: QLoRA
Training Data: BeaverTails + Wiki Toxic + custom curated examples

This model follows the same structured output format but explores the impact of a different base architecture on safety-analysis tasks.

Intended Use

These models are designed for:

✅ Responsible AI research
✅ Moderation decisions
✅ Safety and bias analysis
✅ Human-in-the-loop moderation workflows
✅ Dataset generation and annotation assistance

Post

829

Built a small Streamlit + CLI demo for generating context-dependent toxicity datasets using OpenAI models.

GitHub: https://github.com/Mayukhga83/Toximatics-Contextual-Toxicity-Data-Generator
Demo: https://toximatics-contextual-toxicity-data-generator-fnn9mzm7bkuzmta4.streamlit.app/

The core idea is that the same utterance can become toxic or benign depending on the surrounding social situation. With is generation framework you can create such datasets at scale.

The pipeline supports:

direct context augmentation given the seed utterance
new utterance-context pair generation given seed utterances
multistage generation for diverse examples
validation with a critic model
CSV / JSONL export

Example:

Utterance:
“You are so lucky to work from home.”

Benign context:
A friend congratulates someone on improved work-life balance.

Toxic context:
A colleague dismisses someone struggling with childcare and burnout.

The project is connected to recent work on contextual toxicity understanding https://aclanthology.org/2024.sigdial-1.65/.

View all Posts

models 8

Mayukh Das

AI & ML interests

Recent Activity

Organizations

Posts 2

models 8

Kurapika993/llama-3.1-8b-responsible-ai-safety-lora

Kurapika993/qwen2.5-7b-responsible-ai-qlora

Kurapika993/qwen2.5-7b-qlora-dolly15k

Kurapika993/qwen2.5-7b-qlora-no-robots

Kurapika993/qwen2.5-3b-lora-dolly15k

Kurapika993/qwen2.5-3b-lora-no-robots

Kurapika993/sentiment

Kurapika993/Toxic_classifier_bert

datasets 1

Kurapika993/mini-responsible-ai-instruction-dataset

Mayukh Das

AI & ML interests

Recent Activity

Organizations

Posts 2

models 8 Sort: Recently updated

datasets 1

models 8