Building on HF

Hariprasad Sundaresan PRO

Hari5115

AI & ML interests

LLMs, Fine-tuning, Agentic AI, RAG, Multilingual NLP, Transformers

Recent Activity

updated a model about 14 hours ago

Hari5115/MoleculeIQ-SmolLM2-360M

published a model about 14 hours ago

Hari5115/MoleculeIQ-SmolLM2-360M

reacted to pankajpandey-dev's post with 👍 about 15 hours ago

🧬 Just uploaded K-quants of Carbon-3B for llama.cpp users! @HuggingFaceBio released the original GGUF in bf16 only — so I added the full quant ladder for CPU/edge inference: • Q2_K → 1.4 GB • Q3_K_M → 1.8 GB • Q4_K_M → 2.1 GB ⭐ • Q5_K_M → 2.4 GB • Q6_K → 2.7 GB • Q8_0 → 3.5 GB 🔗 https://huggingface.co/pankajpandey-dev/Carbon-3B-GGUF Now you can generate DNA sequences on your laptop. Needs a llama.cpp build with PR #23410 (HybridDNATokenizer support). Huge thanks to the HuggingFaceBio team for the original model 🙏 #GGUF #llamacpp #genomics #DNA

View all activity

Organizations

None yet

Posts 1

Post

Spanglish. Hinglish. Franglais. Real users don't speak textbook languages 🌍

500M+ Indians type messages like the below example, Most NLP pipelines fail silently on code-switched text, so I built something to start closing that gap for regional language

Fine-tuned MuRIL on 3,000 synthetic Hinglish examples. 97.6% F1.
Not perfect, but open, working, and hopefully useful.

"bhai mera refund kab aayega" → refund_status ✓
"wrong item aaya hai" → exchange_product ✓
"payment cut ho gaya order nahi hua" → payment_issue ✓

🤖 Hari5115/hinglish-retail-intent-classifier
📦 Hari5115/hinglish-retail-intent-dataset
🚀 Hari5115/hinglish-retail-intent-demo

Building for multilingual markets? Have real code-switched data? Would love to connect 🙏

#Hindi #IndianAI #RegionalNLP #NLP #MultilingualAI #OpenSource