🏗️ Building on HF

Kshitij Thakkar PRO

kshitijthakkar

AI & ML interests

Building the evaluation and observability layer for AI. Creator of TraceVerse—turning real-world LLM interactions into datasets, benchmarks, and cost-efficient model insights.

Recent Activity

updated a bucket about 3 hours ago

kshitijthakkar/repro-truthrl-artifacts

published a bucket about 3 hours ago

kshitijthakkar/repro-truthrl-artifacts

updated a bucket about 3 hours ago

kshitijthakkar/repro-memevolve-artifacts

View all activity

Organizations

kshitijthakkar 's Spaces 25

GuardianTails

🐾

Pet Health Intelligence Platform

Repro - How to Correctly Report LLM-as-a-Judge Evaluations

🎯

Log and share LLM evaluation findings in a collaborative notebook

Repro - Dependence-Aware Label Aggregation via Ising Models

🧲

Collaborate with an AI agent via a shared logbook

Repro - A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

🎯

Browse and collaborate on a research logbook with AI assistance

Repro - TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

🎯

Collaborate with an AI agent using a shared logbook

Repro - MemEvolve: Meta-Evolution of Agent Memory Systems

🧬

Collaborate with an AI agent to manage a shared experiment logbook

Repro - BrokenMath: Sycophancy in Theorem Proving

🎯

Explore and collaborate on research logbooks

Repro - Fixed Budget vs Fixed Confidence in Best-Arm Identification

🎰

Explore experiment logs and sync findings with an AI agent

Repro - Dimension-Free KL Bounds for Underdamped Langevin MC

📉

Explore and edit research logbooks with AI collaboration

Repro - PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency

🎯

Explore experiment logs and sync findings with an AI agent

Repro - Row-Stochastic vs Doubly-Stochastic Decentralized Learning

🕸

Explore and sync research logbooks with your coding agent

Repro - A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth

⚖

Explore LLM evaluation logs and collaborate via an agent

Kirigami Journey

🪷

How we carved a 35B MoE to fit a 24GB GPU — zero training

Racing for Chiku — a chiku-inu field report

🐾

chiku-inu's Gemma-challenge contributions & lessons

Loggenix MoE 0.4B-A0.2B Demo

🧠

Test and evaluate the Loggenix MoE language model

E-Commerce Product Content Generator

🛒

Generate product photos and marketing copy for e‑commerce

Multimodal Content Pipeline

🖼

Generate an image and hear its spoken description

AI Content Creation Pipeline

🎨

Generate complete social media posts from a text prompt

Loggenix Moe 0.3B A0.1B Demo

🏢

Demo Space for my model loggenix-moe-0.3B-A0.1B

my_Akatsuki_theme

🚀

Preview and customize `my_Akatsuki_theme` in a Gradio interface

my_naruto_theme

🚀

Explore a Naruto-themed interface with various interactive elements

Trackio

🚀

Visualize and compare experiment metrics and media in Trackio

Trl Trackio

🚀

Display tracking information

Template Final Assignment

🕵

Run GAIA benchmark and submit AI answers