Nikita Kezins's picture

Nikita Kezins

entfane

·

AI & ML interests

LLM post-training, adversarial training, safety, knowledge transfer

Recent Activity

liked a dataset 1 day ago

AmazonScience/FalseReject

liked a dataset 2 days ago

allenai/wildguardmix

updated a model 12 days ago

entfane/baby-math-135m

View all activity

Organizations

upvoted an article 3 months ago

Article

Self-Hosting LLaMA 3.1 70B (or any ~70B LLM) Affordably

Aug 20, 2024

•

27

upvoted 3 collections 3 months ago

Olmo 3 Post-training

All artifacts for post-training Olmo 3. Datasets follow the model that resulted from training on them. • 32 items • Updated Dec 23, 2025 • 49

RLCR

Collection of models and datasets for Beyond Binary Rewards: Training LMs to Reason about their Uncertainty • 10 items • Updated Aug 6, 2025 • 7

Model Merging

Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! • 30 items • Updated Jun 12, 2024 • 250

upvoted 2 collections 4 months ago

Qwen2.5-Math

Math-specific model series based on Qwen2.5 • 11 items • Updated Dec 31, 2025 • 89

Qwen3Guard

7 items • Updated Dec 31, 2025 • 62

upvoted an article 4 months ago

Article

Everything You Need to Know about Knowledge Distillation

Mar 6, 2025

•

66

upvoted a collection 4 months ago

[NeurIPS 2025] RPC Resources

Sampled Reasoning Paths for NeurIPS 2025 Paper: A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning • 6 items • Updated Oct 23, 2025 • 8

upvoted a collection 6 months ago

📐 FineMath

FineMath datasets and ablation models • 14 items • Updated May 5, 2025 • 25

upvoted an article 6 months ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

Mar 26, 2025

•

182

upvoted 2 articles 7 months ago

Article

Illustrating Reinforcement Learning from Human Feedback (RLHF)

+2

Dec 9, 2022

•

397

Article

KV Caching Explained: Optimizing Transformer Inference Efficiency

Jan 30, 2025

•

230

upvoted an article 8 months ago

Article

Uncensor any LLM with abliteration

Jun 13, 2024

•

768

upvoted an article 11 months ago

Article

PyTorchModelHubMixin: Bridging the Gap for Custom AI Models on Hugging Face

Nov 11, 2024

•

20