nicolay-r (Nicolay Rusnachenko)

posted an update 17 days ago

Post

282

📢 Following the bulk-chain v1.1.0 release and its minimalistic integration and real-world deployment on async inference with your LLM provider. Below is an example of tk-sheet for spreadsheet-style LLM reasoning

🔑 We use the concept of asyncio loops. You can set event loop of the utilized framework. At present it converts async generators to sync.
https://stackoverflow.com/questions/71580727/translating-async-generator-into-sync-one/79617639#79617639

🔗 The integration demo:
https://github.com/nicolay-r/bulk-chain-tksheet-client

🌌 The provider:
https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/replicate_104.py

reacted to merve's post with 🔥 17 days ago

Post

2575

It was the week of video generation at @huggingface , on top of many new LLMs, VLMs and more!
Let’s have a wrap 🌯 merve/may-16-releases-682aeed23b97eb0fe965345c

LLMs 💬
> Alibaba Qwen released WorldPM-72B, new World Preference Model trained with 15M preference samples (OS)
> II-Medical-8B, new LLM for medical reasoning that comes in 8B by Intelligent-Internet
> TRAIL is a new dataset by Patronus for trace error reasoning for agents (OS)

Multimodal 🖼️💬
> Salesforce Research released BLIP3o, a new any-to-any model with image-text input and image-text output 💬it’s based on an image encoder, a text decoder and a DiT, and comes in 8B
> They also released pre-training and fine-tuning datasets
> MMMG is a multimodal generation benchmark for image, audio, text (interleaved)

Image Generation ⏯️
> Alibaba Wan-AI released Wan2.1-VACE, video foundation model for image and text to video, video-to-audio and more tasks, comes in 1.3B and 14B (OS)
> ZuluVision released MoviiGen1.1, new cinematic video generation model based on Wan 2.1 14B (OS)
> multimodalart released isometric-skeumorphic-3d-bnb, an isometric 3D asset generator (like AirBnB assets) based on Flux
> LTX-Video-0.9.7-distilled is a new real-time video generation (text and image to video) model by Lightricks
> Hidream_t2i_human_preference is a new text-to-image preference dataset by Rapidata with 195k human responses from 38k annotators

Audio 🗣️
> stabilityai released stable-audio-open-small new text-to-audio model
> TEN-framework released ten-vad, voice activity detection model (OS)

reacted to ginipick's post with 👍 17 days ago

Post

3780

AI BOOK MAKER 📚✨
Transform your text and PDF into a beautiful AI-powered intelligent Flipbook with magic 🪄

ginipick/AI-BOOK

Introduction 🌟
AI BOOK MAKER is a revolutionary platform that converts text and PDF files into intelligent AI books. With just a single file upload, our automatic RAG (Retrieval-Augmented Generation) system activates an AI chatbot that perfectly comprehends your content, delivering a next-generation digital book experience that combines interactive flipbooks with conversational intelligence! 📖✨
Groundbreaking Core Features 💎

One-Click RAG System 🔄: Automatic knowledge base creation and AI conversation engine activation with just one text or PDF upload
Industry-Leading Flip Effects 📄➡️📄: Exclusive AI-driven page transition technology for an immersive experience beyond physical books
Perfect Cross-Platform Support 📱: Intelligent responsive design providing optimized experiences on any device
Automatic Unique URL Generation 🔗: Exclusive system creating personalized links for instant sharing with friends, family, and colleagues
AI Auto-Summary Engine 🤖: Intelligent summarization and insight extraction features that instantly grasp the essence of your content
Ultra-Intelligent AI Chatbot 💬: Personalized knowledge assistant to ask questions and get answers about book content

Game-Changer For People Who 👍

📝 Authors and creators wanting to share their knowledge and content as AI-powered interactive books
🎓 Educators and students looking to transform research materials and learning content into smart, conversational flipbooks
👨‍💼 Professionals seeking to upgrade business documents into intelligent books shareable with clients and team members
📚 Anyone wanting to share valuable documents with their network while exploring new experiences with AI assistance

Start the Magic in 3 Seconds 🛠️

Single Upload 📤
Ultra-Fast AI Conversion ⚡
Custom URL Acquisition 👀
Explore with AI 💬

reacted to reach-vb's post with 👍 17 days ago

Post

3671

hey hey @mradermacher - VB from Hugging Face here, we'd love to onboard you over to our optimised xet backend! 💥

as you know we're in the process of upgrading our storage backend to xet (which helps us scale and offer blazingly fast upload/ download speeds too): https://huggingface.co/blog/xet-on-the-hub and now that we are certain that the backend can scale with even big models like Llama 4/ Qwen 3 - we;re moving to the next phase of inviting impactful orgs and users on the hub over as you are a big part of the open source ML community - we would love to onboard you next and create some excitement about it in the community too!

in terms of actual steps - it should be as simple as one of the org admins to join hf.co/join/xet - we'll take care of the rest.

p.s. you'd need to have a the latest hf_xet version of huggingface_hub lib but everything else should be the same: https://huggingface.co/docs/hub/storage-backends#using-xet-storage

p.p.s. this is fully backwards compatible so everything will work as it should! 🤗

16 replies

·

reacted to AdinaY's post with 🔥 17 days ago

Post

2402

Dolphin 🔥 A multimodal document image parsing model from ByteDance
, built on an analyze-then-parse paradigm.

ByteDance/Dolphin

✨ MIT licensed
✨ Handles text, tables, figures & formulas via:
- Reading-order layout analysis
- Parallel parsing with smart prompts

posted an update 18 days ago

Post

2372

🚀 For those who interested in minimalistic integration of LLMs inferece with predefined reasoning shema, excited to share the latest bulk chain 1.1.0. It represents a no-string solution for deploying your LLM for efficient inference over data iterators.
✨ Key Features:
- Full async inference support + Including streaming mode for real-time output
- simplified inference API
🔗 Check out the repo: https://github.com/nicolay-r/bulk-chain

💡 Special thanks to @RicardoLee for his work on effective async LLaMA-3 deployment that helped shape this release:
https://github.com/RicardoLeeV587/Llama3-FastInference

reacted to Xenova's post with 🔥 about 1 month ago

Post

8078

Introducing the ONNX model explorer: Browse, search, and visualize neural networks directly in your browser. 🤯 A great tool for anyone studying Machine Learning! We're also releasing the entire dataset of graphs so you can use them in your own projects! 🤗

Check it out! 👇
Demo: onnx-community/model-explorer
Dataset: onnx-community/model-explorer
Source code: https://github.com/xenova/model-explorer

reacted to Jaward's post with 🔥👍 about 1 month ago

Post

3118

Finally my first solo preprint is here:) a love letter to the field. Nothing much lol, this is just me trying to finetune my understanding of research behind the recent breakthroughs in reasoning models. It’s a preprint targeting beginners in the field - will eventually make necessary changes later. In the meantime have fun with it:)
Download: https://github.com/Jaykef/Jaykef/blob/main/papers/The-Dawn-of-Thinking-Machines.pdf

reacted to ginipick's post with 👀 about 1 month ago

Post

4679

# ✨ Dream of IKEA: The Future of AI Interior Design ✨

Hello, AI interior design enthusiasts! 🏠 Today I'm thrilled to introduce you to **"Dream of IKEA"** - an amazing project that will completely transform your living spaces!

## 🌟 What Can It Do?

**Dream of IKEA** is a magical tool that uses artificial intelligence to transform your ordinary spaces into the interior design of your dreams! 🪄

- 📸 Simply upload a photo of your room
- 💭 Describe your desired style or concept
- 🎨 The AI will redesign your space with stunning results!

## 🏆 Key Features

- **Diverse Style Selection** - Over 20 design styles including Minimalist, Bohemian, Japanese, Scandinavian, and more
- **User-Friendly Interface** - Beautiful, intuitive UI that anyone can use
- **High-Quality Image Generation** - Amazing quality powered by ControlNet and Stable Diffusion
- **Customizable Prompts** - Create completely personalized designs with your own prompts

## 🛠️ Technical Highlights

This project utilizes cutting-edge AI technology:
- **ControlNet** - Maintains the structure of your original image while transforming the style
- **NormalBae** - Creates natural transformations through 3D structure recognition
- **Stable Diffusion** - The core of high-quality image generation

## 💡 How to Use

1. **Upload a Photo** - Select the space you want to transform
2. **Choose a Style** - Select from Modern, Classic, or Global design styles
3. **Add a Description** - Like "A cozy bedroom with mountain view" to refine your results
4. **Click Generate** - Let the AI work its magic! 🪄✨

## 🔮 Make Your Dream Space a Reality!

What space are you dreaming of? A minimalist Nordic living room? A glamorous Hollywood-style bedroom? Or perhaps a warm Bohemian kitchen? Now you can visualize all your interior design dreams with the help of AI!

## 🚀 Start Now!
ginigen/interior-design

reacted to julien-c's post with 🔥 about 1 month ago

Post

4751

BOOOOM: Today I'm dropping TINY AGENTS

the 50 lines of code Agent in Javascript 🔥

I spent the last few weeks working on this, so I hope you will like it.

I've been diving into MCP (Model Context Protocol) to understand what the hype was all about.

It is fairly simple, but still quite powerful: MCP is a standard API to expose sets of Tools that can be hooked to LLMs.

But while doing that, came my second realization:

Once you have a MCP Client, an Agent is literally just a while loop on top of it. 🤯

➡️ read it exclusively on the official HF blog: https://huggingface.co/blog/tiny-agents

1 reply

·

reacted to as-cle-bert's post with 🔥 about 1 month ago

Post

2917

Ever dreamt of ingesting into a vector DB that pile of CSVs, Word documents and presentations laying in some remote folders on your PC?🗂️
What if I told you that you can do it within three to six lines of code?🤯
Well, with my latest open-source project, 𝐢𝐧𝐠𝐞𝐬𝐭-𝐚𝐧𝐲𝐭𝐡𝐢𝐧𝐠 (https://github.com/AstraBert/ingest-anything), you can take all your non-PDF files, convert them to PDF, extract their text, chunk, embed and load them into a vector database, all in one go!🚀
How? It's pretty simple!
📁 The input files are converted into PDF by PdfItDown (https://github.com/AstraBert/PdfItDown)
📑 The PDF text is extracted using LlamaIndex readers
🦛 The text is chunked exploiting Chonkie
🧮 The chunks are embedded thanks to Sentence Transformers models
🗄️ The embeddings are loaded into a Qdrant vector database

And you're done!✅
Curious of trying it? Install it by running:

𝘱𝘪𝘱 𝘪𝘯𝘴𝘵𝘢𝘭𝘭 𝘪𝘯𝘨𝘦𝘴𝘵-𝘢𝘯𝘺𝘵𝘩𝘪𝘯𝘨

And you can start using it in your python scripts!🐍
Don't forget to star it on GitHub and let me know if you have any feedback! ➡️ https://github.com/AstraBert/ingest-anything

5 replies

·

posted an update about 1 month ago

Post

2669

🚀 Delighted to share a major milestone in adapting reasoning techniques for data collections augmentation!
Introducing bulk-chain 1.0.0 -- the first major release of a no-string API for adapting your LLM for Chain-of-Thought alike reasoning over records with large amount of parameters across large datasets.

⭐ Check it out: https://github.com/nicolay-r/bulk-chain

What’s new and why it matters:
📦 Fully no-string API for easy client deployment
🔥 Demos are now standalone projects:

Demos:
📺 bash / shell (dispatched): https://github.com/nicolay-r/bulk-chain-shell
📺 tksheet: https://github.com/nicolay-r/bulk-chain-tksheet-client

Using nlp-thirdgate to host the supported providers:
🌌 LLM providers: https://github.com/nicolay-r/nlp-thirdgate

reacted to fdaudens's post with 🤯 about 2 months ago

Post

4138

🎨 Designers, meet OmniSVG! This new model helps you create professional vector graphics from text/images, generate editable SVGs from icons to detailed characters, convert rasters to vectors, maintain style consistency with references, and integrate into your workflow.

@OmniSVG

2 replies

·

posted an update about 2 months ago

Post

642

📢 For those who interested to adopt remote llama-4 for reasoning over your data. So far replicate started to support LLama-4-maverick-instruct, and sharing the uipdated wrapper for bulk-chain framework:

https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/replicate_104.py

bulk-chain: https://github.com/nicolay-r/bulk-chain-shell
Model: meta-llama/Llama-4-Maverick-17B-128E-Original

posted an update 2 months ago

Post

1768

📢 For those who in textual IR and experimenting with quick deployment of CoT / reasoning, the following update might be relevant. I am happy to announce new version of the bulk-chain 0.25.3. It is a no-string framework for quick application of reasoning schema adaptation over your data.

https://github.com/nicolay-r/bulk-chain/releases/tag/0.25.3

The latest release brings huge updates on:
✅ Reforged mechanism of models inference that work in steraming mode.
- Callbacks support for streaming mode (earlier only in demo)
- Deployment of various clients (shell, tksheet; see attachment)
✅ Support for batching (earlier in API mode only)
✅ Optional caching of inferred data in SQlite (always enabled earlier)
- This now makes possible to faster launch small (but mighty) LLMs

🌟 Project: https://github.com/nicolay-r/bulk-chain
🌌 Proviers: https://github.com/nicolay-r/nlp-thirdgate

posted an update 3 months ago

Post

1671

The Concept behind xLSTM has recently turn into the xLSTM-7B model that showcase the performance in the category of the similar-scale Gemma 7B, LLama2 7B, FlaconMamba 7B but with higher performing Inference Kernel

Model: NX-AI/xLSTM-7b
Paper: https://arxiv.org/abs/2503.13427

1 reply

·

posted an update 3 months ago

Post

674

📢 Several weeks ago Microsoft announced Phi-4. My most-recent list of LLM models have had only wrapper for Phi-2, so it was time to update! With this post, happy to share that Phi-4 wrapper is now available at nlp-thirdgate for adopting Chain-of-Thought reasoning:

🤖 https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/transformers_phi4.py

📒 https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_phi4.py

Findings on adaptation: I was able to reproduce only the pipeline based model launching. This version is for textual llm only. Microsoft also released multimodal Phi-4 which is out of scope of this wrapper.

🌌 nlp-thirdgate: https://lnkd.in/ef-wBnNn

posted an update 3 months ago

Post

1134

📢 Delighted to announce the updated version of the no-string framework for chain-of-thought application over JSONL/CSV data:
https://github.com/nicolay-r/bulk-chain/releases/tag/0.25.2

🔧 Fixes:
- Fixed issues with batching mode
- Fixed problem with parsing and passing args in shell mode

⚠️ Limitation: bathing mode is still available only via API.

📒 Quick Start with Gemma-3 in batching mode: https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_gemma_3.ipynb

replied to their post 3 months ago

The important comment is to use the very latest version of the bulk-chain from github which fixes the bug for double-inference in batching.

Nicolay Rusnachenko

AI & ML interests

Recent Activity

Organizations

nicolay-r's activity