Skip to content
View ParagEkbote's full-sized avatar
🪧
https://paragekbote.github.io/
🪧
https://paragekbote.github.io/

Block or report ParagEkbote

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. 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
ParagEkbote/README.md

Typing SVG

Machine Learning Engineer working on transformer-based models, systems and ML infra.

I actively contribute to open-source machine learning projects: contributions.md

Focus areas:

  • Large Language Models and the Hugging Face ecosystem.
  • Parameter-efficient fine-tuning (LoRA / PEFT).
  • LLM inference benchmarking and optimization.
  • Reproducible ML experimentation and open-source tooling.

Profiles

Portfolio

To know more about my work and projects: 🌠 https://paragekbote.github.io/

Pinned Loading

  1. quantized-containerized-models quantized-containerized-models Public

    Deploy AI models with an API through quantization and containerization.

    Python 1

  2. FineWiki Multilingual Tokenizer Anal... FineWiki Multilingual Tokenizer Analysis based on the Smol Training Playbook: https://huggingface.co/spaces/HuggingFaceTB/smol-training-playbook#the-tokenizer
    1
    #!/usr/bin/env python3
    2
    """
    3
    Tokenizer Performance Comparison Script
    4
    5
    A comprehensive tool for evaluating tokenizer efficiency across multiple languages.
  3. hf-model-inspector hf-model-inspector Public

    A package and gh-action to generate quality reports on Hugging Face model stats and usage, addressing ambiguity in open model releases.

    Python 1

  4. Pruna Smash Setup for SmollM Collect... Pruna Smash Setup for SmollM Collection: https://huggingface.co/collections/AINovice2005/smollm-smashed-tiny-giants-optimized-for-speed-68e16113d90eab12bae42a34
    1
    import torch
    2
    from transformers import AutoModelForCausalLM, AutoTokenizer
    3
    from pruna import smash, SmashConfig
    4
    
                  
    5
    # Define per-model Smash + torch.compile configs
  5. ParagEkbote.github.io ParagEkbote.github.io Public

    Code for my personal website, powered by Material for MkDocs.

    HTML