Skip to content
View Kirili4ik's full-sized avatar
🌏
🌏

Block or report Kirili4ik

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Kirili4ik/README.md

Hello there! I'm Kirill 👋🏻

Currently I am a Researcher at AI Agents Team at Jetbrains and a TUM Student 👨‍🎓 at Mathematics in Data Science program.

In the team we are exploring the capabilities of distillation of LLMs for AI Agents.

Previously I was an NLP engineer at Eva AI. Most of the time there I was working on creating long-term memory for our chat bot (T5 for summarization & question-generation, BERT-like quantized and distilled classifiers, building RAG from scratch, etc.)

In 2021 I graduated👨‍🎓 from BCs Applied Mathematics and Informatics and now I'm happy to share my experience leading practical lessons at DL course at the faculty of CS.

In my spare time, I like learning something new about DL and spreading the knowledge to others. For more information, please check my pinned projects, presentations or CV 🤗

Field of interests: NLP, DL for Audio, Generative Models

🛠️ Skills

  • Programming:  Python, C++, SQL
  • ML/DL:      PyTorch, NumPy, SciPy, pandas, scikit-learn
  • Applications:   git, bash, Docker

📊 General GitHub stats:                                         ℹ️ More info about me: 

👨‍🏫 Projects:

Pinned Loading

  1. Deep-Generative-Models Deep-Generative-Models Public

    Deep Generative Models that I have implemented, trained and experimented with.

  2. ruDialoGpt3-finetune-colab ruDialoGpt3-finetune-colab Public

    Ready-for-use-colab tutorial for finetuning ruDialoGpt3 model on а telegram chat using HuggingFace and PyTorch

    Jupyter Notebook 32 7

  3. kws-attention-pytorch kws-attention-pytorch Public

    Keyword spotting for audio with attention (KWS model for audio)

    Jupyter Notebook 18 4

  4. QuartzNet-ASR-pytorch QuartzNet-ASR-pytorch Public

    Automatic Speech Recognition (ASR) model QuartzNet trained on English CommonVoice. In PyTroch with CTC loss and beam search.

    Jupyter Notebook 16 3

  5. iad-deep-learning iad-deep-learning Public

    Forked from hse-ds/iad-deep-learning

    Курс "Современные методы машинного обучения" на майноре ИАД

    Jupyter Notebook 4

  6. pres-n-articles pres-n-articles Public

    Some of the presentations, articles, reports I've written.