Nicolay Rusnachenko

nicolay-r

https://nicolay-r.github.io/

AI & ML interests

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

Recent Activity

posted an update about 7 hours ago

📢 Replicate IO just started support 🐋 DeepSeek-R1 hosting! https://replicate.com/deepseek-ai/deepseek-r1 If you wish to quick start with reasoning over your dataset data, I just added support at Replicate provider for bulk-chain: https://github.com/nicolay-r/nlp-thirdgate/blob/ebcdec156eb43f9c32d0d70aadc2d26765d31b75/llm/replicate_104.py#L14-L21 🔧 What I fixed (see my setups in the second screenshot) - 🌡️default temperature is 0.6 - ❌ no system prompt Here is a quick start for applying R1 for reasoning over your data (see first screenshot): https://github.com/nicolay-r/bulk-chain?tab=readme-ov-file#shell 🚀 Perfomance: ~24 tokens / sec. In my experience the peformance is way more faster than at OpenRouter, similar to playground 💵 Price: 10 USD / 10 USD per 1M tokens 🌟 bulk-chain: https://github.com/nicolay-r/bulk-chain

liked a model 1 day ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

reacted to clem's post with 🚀 1 day ago

The 🐳 just crossed 10,000 followers on HF https://huggingface.co/deepseek-ai

View all activity

Organizations

None yet

nicolay-r's activity

upvoted a collection 4 days ago

DeepSeek-R1

Collection

8 items • Updated 10 days ago • 301

upvoted a paper 14 days ago

HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs

Paper • 2412.18925 • Published Dec 25, 2024 • 97

upvoted 2 papers about 2 months ago

Stream of Search (SoS): Learning to Search in Language

Paper • 2404.03683 • Published Apr 1, 2024 • 30

STaR: Bootstrapping Reasoning With Reasoning

Paper • 2203.14465 • Published Mar 28, 2022 • 8

upvoted an article about 2 months ago

Article

Reverse Thinking Makes LLMs Stronger Reasoners

•

Dec 3, 2024

• 2

upvoted an article 4 months ago

Article

SeeMoE: Implementing a MoE Vision Language Model from Scratch

•

Jun 23, 2024

• 34

upvoted a paper 4 months ago

LML: Language Model Learning a Dataset for Data-Augmented Prediction

Paper • 2409.18957 • Published Sep 27, 2024 • 10

upvoted a collection 6 months ago

Chinchunmei on WASSA2024 Shared-Task 1

Collection

This is the model cards collection for Chinchunmei team in the WASSA2024 Shared-Task 1: Empathy Detection and Emotion Classification. • 5 items • Updated Jul 3, 2024 • 2

upvoted 2 papers 8 months ago

PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits

Paper • 2305.02547 • Published May 4, 2023 • 7

Personality Traits in Large Language Models

Paper • 2307.00184 • Published Jul 1, 2023 • 20

upvoted 2 articles 9 months ago

Article

Vision Language Models Explained

Apr 11, 2024

• 248

Article

Fine-tune Llama 3 with ORPO

•

Apr 22, 2024

• 233

upvoted 8 papers 10 months ago

RuSentNE-2023: Evaluating Entity-Oriented Sentiment Analysis on Russian News Texts

Paper • 2305.17679 • Published May 28, 2023 • 1

Large Language Models in Targeted Sentiment Analysis

Paper • 2404.12342 • Published Apr 18, 2024 • 2

Visual CoT: Unleashing Chain-of-Thought Reasoning in Multi-Modal Language Models

Paper • 2403.16999 • Published Mar 25, 2024 • 4

RegionGPT: Towards Region Understanding Vision Language Model

Paper • 2403.02330 • Published Mar 4, 2024 • 2

Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring

Paper • 2403.09333 • Published Mar 14, 2024 • 15

Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models

Paper • 2404.07973 • Published Apr 11, 2024 • 31

Rho-1: Not All Tokens Are What You Need

Paper • 2404.07965 • Published Apr 11, 2024 • 90

OmniFusion Technical Report

Paper • 2404.06212 • Published Apr 9, 2024 • 75