Nicolay Rusnachenko

nicolay-r

AI & ML interests

Information Retrieval・Medical Multimodal NLP (🖼+📝) Research Fellow @BU_Research・software developer http://arekit.io・PhD in NLP

Recent Activity

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

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

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

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

posted an update 2 days ago

🚀 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

View all activity

Organizations

None yet

nicolay-r's activity

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

Post

3412

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 🔥 1 day ago

Post

2701

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

4 replies

posted an update 2 days ago

Post

2072

🚀 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 🤯 17 days ago

Post

4086

🎨 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 19 days ago

Post

594

📢 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 24 days ago

Post

1764

📢 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 about 1 month ago

Post

1666

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 about 1 month ago

Post

672

📢 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 about 1 month ago

Post

1132

📢 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 about 1 month 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.

posted an update about 2 months ago

Post

1582

📢 With the recent release of Gemma-3, If you interested to play with textual chain-of-though, the notebook below is a wrapper over the the model (native transformers inference API) for passing the predefined schema of promps in batching mode.
https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_gemma_3.ipynb

Limitation: schema supports texts only (for now), while gemma-3 is a text+image to text.

Model: google/gemma-3-1b-it
Provider: https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/transformers_gemma3.py

1 reply

reacted to onekq's post with 👀 about 2 months ago

Post

1415

The performance of deepseek-r1-distill-qwen-32b is abysmal. I know Qwen instruct (not coder) is quite poor on coding. As such, I have low expectation on other R1 repro works also based on Qwen instruct too. onekq-ai/r1-reproduction-works-67a93f2fb8b21202c9eedf0b

This makes it particularly mysterious what went into QwQ-32B? Why did it work so well? Was it trained from scratch? Anyone has insights about this?
onekq-ai/WebApp1K-models-leaderboard

5 replies

replied to ritvik77's post about 2 months ago

@ritvik77 , sounds good on your plans! Meanwhile looking forward to adapt 7B version to experiment in radiology domain. Happy to read more on that and once and if it gets to the paper, so I can populate the survey of the related advances.

replied to ritvik77's post about 2 months ago

@ritvik77 , excited to run into this! Is the paper and studies behind it on arxiv or elsewhere?

reacted to ritvik77's post with 🔥 about 2 months ago

Post

1533

Try it out: ritvik77/Medical_Doctor_AI_LoRA-Mistral-7B-Instruct_FullModel

🩺 Medical Diagnosis AI Model - Powered by Mistral-7B & LoRA 🚀
🔹 Model Overview:
Base Model: Mistral-7B (7.7 billion parameters)
Fine-Tuning Method: LoRA (Low-Rank Adaptation)
Quantization: bnb_4bit (reduces memory footprint while retaining performance)
🔹 Parameter Details:
Original Mistral-7B Parameters: 7.7 billion
LoRA Fine-Tuned Parameters: 4.48% of total model parameters (340 million) Final Merged Model Size (bnb_4bit Quantized): ~4.5GB

This can help you in making a AI agent for healthcare, if you need to finetune it for JSON function/tool calling format you can use some medical function calling dataset to again fine fine tine on it.

3 replies

reacted to clem's post with ❤️ about 2 months ago

Post

4698

10,000+ models based on Deepseek R1 have been publicly shared on Hugging Face! Which ones are your favorite ones: https://huggingface.co/models?sort=trending&search=r1. Truly game-changer!

reacted to Jaward's post with 🔥👀 about 2 months ago

Post

2592

Lightweight (nanoGPT) implementation of hybrid norm - an intuitive normalization method that combines the strength of both pre-norm (i.e QKV-norm in MHA) and post-norm in the feed-forward network.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/hybrid_normalization.ipynb

replied to ychen's post about 2 months ago

@ychen , I see. I was expecting your findings were a part of the phd program. Take your time with publications then, since it is common while at Phd. It would be great to have a paper during the masters and all the best with it!

replied to ychen's post about 2 months ago

@ychen Good luck with your studies and pleased for affecting on your advances in it. Are you on google scholar or github with personal advances in this domain?