Malikeh Ehghaghi

Malikeh1375's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 7 days ago

TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior

Paper • 2512.20757 • Published 14 days ago • 16

upvoted a collection 22 days ago

TokSuite Tokenization Robustness Benchmark

Collection

34 items • Updated Oct 29, 2025 • 1

upvoted a collection 4 months ago

TokSuite Model Collection

Collection

14 items • Updated Oct 28, 2025 • 2

upvoted 3 papers 6 months ago

Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM

Paper • 2403.07816 • Published Mar 12, 2024 • 44

Distillation Scaling Laws

Paper • 2502.08606 • Published Feb 12, 2025 • 47

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

Paper • 2506.05209 • Published Jun 5, 2025 • 59

upvoted a collection 8 months ago

supertoken

Collection

The initial checkpoints for the token comparison research. • 20 items • Updated May 22, 2025 • 2

upvoted a collection 9 months ago

Gemstone Models

Collection

Our 22 open source Gemstone models for scaling laws range from 50M to 2B parameters, spanning 11 widths from 256 to 3072 and 18 depths from 3 to 80. • 69 items • Updated Jul 4, 2025 • 10

upvoted 2 papers about 1 year ago

Revealing the Barriers of Language Agents in Planning

Paper • 2410.12409 • Published Oct 16, 2024 • 27

EchoPrime: A Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation

Paper • 2410.09704 • Published Oct 13, 2024 • 14

upvoted a collection over 1 year ago

LLM Reasoning Papers

Collection

Papers to improve reasoning capabilities of LLMs • 20 items • Updated Jan 15, 2025 • 123

upvoted a paper over 1 year ago

Training Language Models to Self-Correct via Reinforcement Learning

Paper • 2409.12917 • Published Sep 19, 2024 • 140

upvoted 3 collections over 1 year ago

Qwen2.5

Collection

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 46 items • Updated 7 days ago • 673

Korean Datasets I've released so far.

Collection

지금까지 업로드한 한국어 데이터셋 콜렉션입니다. • 8 items • Updated May 24, 2024 • 21

Arabic Light Benchmarks

Collection

10% sample of the original benchmarks for each dataset from lighteval • 7 items • Updated Sep 10, 2024 • 2

upvoted an article over 1 year ago

view article

Article

Llama-3.1-Storm-8B: Improved SLM with Self-Curation + Model Merging

• 

Aug 19, 2024

•

79

upvoted a collection over 1 year ago

Arabic ORPO-DPO Datasets

Collection

12 items • Updated Aug 17, 2024 • 2

upvoted 3 papers over 1 year ago

AgentInstruct: Toward Generative Teaching with Agentic Flows

Paper • 2407.03502 • Published Jul 3, 2024 • 51

Qwen2 Technical Report

Paper • 2407.10671 • Published Jul 15, 2024 • 167

BOND: Aligning LLMs with Best-of-N Distillation

Paper • 2407.14622 • Published Jul 19, 2024 • 20