Open to Work

12 8 8

Rakshit Aralimatti

RakshitAralimatti

AI & ML interests

Nvidia

Recent Activity

reacted to ovi054's post with 🔥 6 days ago

Introducing Anim Lab AI⚡ My submission for the MCP 1st Birthday Hackathon Turn any math concept or logic into a clear video explanation instantly using AI. 👉 Try it now: https://huggingface.co/spaces/MCP-1st-Birthday/anim-lab-ai Demo outputs are attached 👇

upvoted an article 9 days ago

Continuous batching from first principles

replied to their post 21 days ago

OCR has absolutely blown up in 2025, and honestly, my perspective on document processing has completely changed. This year has been wild. Vision Language Models like Nanonets OCR2-3B hit the scene and suddenly we're getting accuracy on complex forms (vs for traditional OCR). We're talking handwritten checkboxes, watermarked documents, multi-column layouts, even LaTeX equations all handled in a single pass. The market numbers say it all: OCR accuracy passed 98% for printed text, AI integration is everywhere, and real-time processing is now standard. The entire OCR market is hitting $25.13 billion in 2025 because this tech actually works now. I wrote a detailed Medium article walking through: 1. Why vision LMs changed the game 2. NVIDIA NeMo Retriever architecture 3. Complete code breakdown 4. Real government/healthcare use cases 5. Production deployment guide Article: https://medium.com/@rakshitaralimatti2001/nvidia-nemo-retriever-ocr-building-document-intelligence-systems-for-enterprise-and-government-42a6684c37a1 Try It Yourself

View all activity

Organizations

reacted to ovi054's post with 🔥 6 days ago

Post

6006

Introducing Anim Lab AI⚡

My submission for the MCP 1st Birthday Hackathon

Turn any math concept or logic into a clear video explanation instantly using AI.

👉 Try it now: MCP-1st-Birthday/anim-lab-ai

Demo outputs are attached 👇

upvoted an article 9 days ago

Article

Continuous batching from first principles

13 days ago

•

243

replied to their post 21 days ago

Modern OCR in healthcare is extremely reliable when implemented correctly. I've personally built OCR + RAG systems for healthcare clients, and the results have been remarkable.

posted an update 23 days ago

Post

1367

OCR has absolutely blown up in 2025, and honestly, my perspective on document processing has completely changed.

This year has been wild. Vision Language Models like Nanonets OCR2-3B hit the scene and suddenly we're getting accuracy on complex forms (vs for traditional OCR). We're talking handwritten checkboxes, watermarked documents, multi-column layouts, even LaTeX equations all handled in a single pass.

The market numbers say it all: OCR accuracy passed 98% for printed text, AI integration is everywhere, and real-time processing is now standard. The entire OCR market is hitting $25.13 billion in 2025 because this tech actually works now.

I wrote a detailed Medium article walking through:

1. Why vision LMs changed the game
2. NVIDIA NeMo Retriever architecture
3. Complete code breakdown
4. Real government/healthcare use cases
5. Production deployment guide

Article: https://medium.com/@rakshitaralimatti2001/nvidia-nemo-retriever-ocr-building-document-intelligence-systems-for-enterprise-and-government-42a6684c37a1

Try It Yourself

3 replies

upvoted an article about 1 month ago

Article

Supercharge your OCR Pipelines with Open Models

Oct 21

•

273

upvoted an article about 2 months ago

Article

SOTA OCR with Core ML and dots.ocr

Oct 2

•

upvoted an article 2 months ago

Article

Deploy NVIDIA Riva ASR on Kubernetes GPU Cluster in Just 5 Minutes

Sep 5

•

reacted to prithivMLmods's post with 🔥 3 months ago

Post

3141

I'm a Hugging Face Fellow now, guys!🤗❤️

With the same passion, trust, and momentum to contribute to the community, I’m excited to do some amazing things to wrap up Q3 and Q4 of 2025. And importantly, I’ve been lucky enough to receive some knowledge and guidance from @merve to build open-source demos and stuff. Thank you for the belief.

Thank you — much love.
Long live open source!

— Prithiv

published an article 3 months ago

Article

Deploy NVIDIA Riva ASR on Kubernetes GPU Cluster in Just 5 Minutes

Sep 5

•

replied to andywu-kby's post 3 months ago

I tried it, Its very COOL.

posted an update 3 months ago

Post

261

Have you ever wanted to easily deploy a cutting-edge speech recognition system that actually works in real time? How about one powered by NVIDIA GPUs on Kubernetes, but without the headache of complicated installs?

Well, your wait is over! My latest blog shows how to deploy NVIDIA Riva ASR in just 5 minutes using Helm charts. From validating GPU readiness in Kubernetes to customizing your ASR models and spinning up the service, this guide covers it all.
Read it here - https://medium.com/@rakshitaralimatti2001/deploy-nvidia-riva-asr-on-kubernetes-gpu-ready-in-minutes-30955d6ed7b8

BONUS: I even built simple Streamlit apps so you can test with your mic or upload audio files to see the magic live.

✨ Bookmark this post and the blog for your next voice AI project or production-ready speech application!

reacted to ACloudCenter's post with 🔥 3 months ago

Post

1847

I've really been into testing the various ASR, TTS, and other audio related models. This space showcases the Nvidia Canary-Qwen 2.5B model. The model is able to transcribe incredibly fast and and combine qwen for queries about the transcript.

All audio example files were generated with my adjacent VibeVoice Conference Generator Space. Another really cool model!!
ACloudCenter/canary-qwen-transcriber-2.5b

2 replies

reacted to codelion's post with 🔥 3 months ago

Post

6180

I recently worked on a LoRA that improves tool use in LLM. Thought the approach might interest folks here.

The issue I have had when trying to use some of the local LLMs with coding agents is this:

Me: "Find all API endpoints with authentication in this codebase"
LLM: "You should look for @app .route decorators and check if they have auth middleware..."

But I often want it to search the files and show me but the LLM doesn't trigger a tool use call.

To fine-tune it for tool use I combined two data sources:

1. Magpie scenarios - 5000+ diverse tasks (bug hunting, refactoring, security audits)
2. Real execution - Ran these on actual repos (FastAPI, Django, React) to get authentic tool responses

This ensures the model learns both breadth (many scenarios) and depth (real tool behavior).

Tools We Taught:
- read_file - Actually read file contents
- search_files - Regex/pattern search across codebases
- find_definition - Locate classes/functions
- analyze_imports - Dependency tracking
- list_directory - Explore structure
- run_tests - Execute test suites

Improvements:
- Tool calling accuracy: 12% → 80%
- Correct parameters: 8% → 87%
- Multi-step tasks: 3% → 78%
- End-to-end completion: 5% → 80%
- Tools per task: 0.2 → 3.8

The LoRA really improves on intential tool call as an example consider the query: "Find ValueError in payment module"

The response proceeds as follows:

1. Calls search_files with pattern "ValueError"
2. Gets 4 matches across 3 files
3. Calls read_file on each match
4. Analyzes context
5. Reports: "Found 3 ValueError instances: payment/processor.py:47 for invalid amount, payment/validator.py:23 for unsupported currency..."

Resources:
- Colab notebook https://colab.research.google.com/github/codelion/ellora/blob/main/Ellora_Recipe_3_Enhanced_Tool_Calling_and_Code_Understanding.ipynb
- Model - codelion/Llama-3.2-1B-Instruct-tool-calling-lora
- GitHub - https://github.com/codelion/ellora

reacted to codelion's post with 🔥 3 months ago

Post

5276

I wanted to share a technique that's been working really well for recovering performance after INT4 quantization.

Typically, quantizing the LLM to INT4 (unlike say INT8) for inference can incur some accuracy loss. Instead of accepting the quality loss, we used the FP16 model as a teacher to train a tiny LoRA adapter (rank=16) for the quantized model. The cool part: the model generates its own training data using the Magpie technique so no external datasets needed. This is critical because we want to remain as much as possible in the distribution of the model's natural responses.

Last year Apple's foundational models paper (https://arxiv.org/pdf/2407.21075) had proposed a similar technique and found "By using accuracy-recovery LoRA adapters with only rank 16, Alpaca win rate can be improved by 7-18%, GMS8K accuracy is boosted by 5-10%." (page 47).

We saw similar results on Qwen3-0.6B:

Perplexity: 2.40 → 2.09 (only 5.7% degradation from FP16 baseline)
Memory: Only 0.28GB vs 1.0GB for FP16 (75% reduction)
Speed: 3.0x faster inference than FP16
Quality: Generates correct, optimized code solutions

- Pre-trained adapter: codelion/Qwen3-0.6B-accuracy-recovery-lora
- GitHub repo: https://github.com/codelion/ellora

Happy to answer questions about the implementation or help anyone trying to replicate this. The key insight is that quantization errors are systematic and learnable - a small adapter can bridge the gap without negating the benefits of quantization.

Has anyone else experimented with self-distillation for quantization recovery? Would love to hear about different approaches!

replied to their post 4 months ago

Thanks @treehugg3 for the thoughtful feedback! 🙏 My main motive here was to break it down in simple words for people who are new to AI or just starting to learn about reasoning models. I completely understand your concern I’ll make sure to include more detailed explanations, examples, sources, and technical depth (like backtracking and novel reasoning paths) in upcoming blogs. Really appreciate your input, it helps me improve!

replied to their post 4 months ago

Thanks @Edalexan .Glad that you found it useful.

commented on What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware 4 months ago

Hi @itschandra09 , the E2M1 structure is 1 sign bit, 2 exponent bits, and 1 mantissa bit.
sorry for wrong image.

posted an update 4 months ago

Post

6786

When you ask ChatGPT, Claude, or Gemini a really tough question,
you might notice that little "thinking..." moment before it answers.

But what does it actually mean when an LLM is “thinking”?

Imagine a chess player pausing before their next move not because they don’t know how to play, but because they’re running through possibilities, weighing options, and choosing the best one.
LLMs do something similar… except they’re not really thinking like us.

Here’s the surprising part :-
You might think these reasoning skills come from futuristic architectures or alien neural networks.
In reality, most reasoning LLMs still use the same transformer decoder-only architecture as other models
The real magic?
It’s in how they’re trained and what data they learn from.

Can AI actually think, or is it just insanely good at faking it?
I broke it down in a simple, 4-minute Medium read.
Bet you’ll walk away with at least one “aha!” moment. 🚀

Read here - https://lnkd.in/edZ8Ceyg

9 replies

commented on What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware 4 months ago

This comment has been hidden

upvoted an article 4 months ago

Article

What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware

Aug 8

•

Rakshit Aralimatti

AI & ML interests

Recent Activity

Organizations