alkinun's picture

alkinun PRO

AtAndDev

·

AI & ML interests

LLMs, Alignment, Merging, Unsloth, DPO, SFT, ORPO, SPIN..

Recent Activity

updated a dataset about 6 hours ago

MoLA-LLM/OpenHelix-R-86k-8-tasks

published a dataset about 6 hours ago

MoLA-LLM/OpenHelix-R-86k-8-tasks

updated a dataset about 7 hours ago

MoLA-LLM/OpenHelix-R-86k-16-tasks

View all activity

Organizations

upvoted an article 2 days ago

Article

Curation is All You Need

By

•

19 days ago

• 2

upvoted a collection 2 days ago

NVIDIA Nemotron

Open, Production-ready Enterprise Models. Nvidia Open Model license. • 3 items • Updated 2 days ago • 39

upvoted a collection 4 days ago

👁️ LFM2-VL

LFM2-VL is our first series of vision-language models, designed for on-device deployment. • 6 items • Updated 1 day ago • 31

upvoted 2 articles 6 days ago

Article

Fine Tuning Gemma 3 For Human Alignment

By

•

May 17

• 4

Article

AHA Leaderboard

By

•

Mar 30

• 4

upvoted an article 9 days ago

Article

Introducing : 🤏🏻🏭SmolFactory

By

•

10 days ago

• 5

upvoted a paper 15 days ago

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Paper • 2406.01574 • Published Jun 3, 2024 • 51

upvoted an article 15 days ago

Article

LLM agent experiment with a purpose-built RPG and tool calls. (Work in progress)

By

•

15 days ago

• 7

upvoted a collection 17 days ago

cool datasets

188 items • Updated 5 days ago • 18

upvoted an article 18 days ago

Article

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

By

and 4 others •

23 days ago

• 156

upvoted an article 20 days ago

Article

AutoBench Run 2 Results are Out! Surprise: Gemini 2.5 Pro is not the Best Affordable Thinking Model

By

•

Apr 29

• 6

upvoted 3 collections 26 days ago

JSON Mode Reasoning

A collection of structured outputs reasoning dataset • 3 items • Updated 29 days ago • 3

Tool Use Reasoning

A collection of tool use reasoning dataset in Hermes format • 5 items • Updated 29 days ago • 8

Qwen3

84 items • Updated 14 days ago • 1.11k

upvoted 4 articles about 1 month ago

Article

Create Mixtures of Experts with MergeKit

By

•

Mar 28, 2024

• 22

Article

Merge Large Language Models with mergekit

By

•

Jan 9, 2024

• 134

Article

<p style="text-align:center;"> Bourbaki (7b): SOTA 7B Algorithms for Putnam Bench (Part I: Reasoning MDPs)</p>

By

and 2 others •

Jul 13

• 11

Article

SmolLM3: smol, multilingual, long-context reasoner

By

and 22 others •

Jul 8

• 631

upvoted a paper about 2 months ago

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

Paper • 2410.01215 • Published Oct 2, 2024 • 36

upvoted a collection about 2 months ago

Gemma 3n

4 items • Updated Jul 10 • 214