Kalle Hilsenbek

Bachstelze's activity

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

commented a paper about 1 month ago

Softpick: No Attention Sink, No Massive Activations with Rectified Softmax

Paper • 2504.20966 • Published Apr 29 • 31 •

5

commented a paper 2 months ago

A Refined Analysis of Massive Activations in LLMs

Paper • 2503.22329 • Published Mar 28 • 14 •

3

commented 2 papers 4 months ago

How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training

Paper • 2502.11196 • Published Feb 16 • 22 •

6

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published Jan 28 • 122 •

6

New activity in answerdotai/ModernBERT-base 5 months ago

ModernBART wen?

👍 3

6

#38 opened 5 months ago by

Fizzarolli

New activity in HuggingFaceTB/SmolLM2-360M-Instruct 7 months ago

Adding Evaluation Results

1

#6 opened 7 months ago by

leaderboard-pr-bot

commented 2 papers 8 months ago

Emergent properties with repeated examples

Paper • 2410.07041 • Published Oct 9, 2024 • 8 •

3

Differential Transformer

Paper • 2410.05258 • Published Oct 7, 2024 • 179 •

36

commented 2 papers 9 months ago

Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction

Paper • 2409.17422 • Published Sep 25, 2024 • 26 •

5

EuroLLM: Multilingual Language Models for Europe

Paper • 2409.16235 • Published Sep 24, 2024 • 26 •

4

commented 4 papers 10 months ago

BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline

Paper • 2408.15079 • Published Aug 27, 2024 • 55 •

4

Dolphin: Long Context as a New Modality for Energy-Efficient On-Device Language Models

Paper • 2408.15518 • Published Aug 28, 2024 • 43 •

4

Better Alignment with Instruction Back-and-Forth Translation

Paper • 2408.04614 • Published Aug 8, 2024 • 16 •

3

Gemma 2: Improving Open Language Models at a Practical Size

Paper • 2408.00118 • Published Jul 31, 2024 • 77 •

3

commented a paper 11 months ago

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

Paper • 2407.02490 • Published Jul 2, 2024 • 26 •

4

commented 2 papers 12 months ago

Breaking the Attention Bottleneck

Paper • 2406.10906 • Published Jun 16, 2024 • 4 •

4

Breaking the Attention Bottleneck

Paper • 2406.10906 • Published Jun 16, 2024 • 4 •

4

commented a paper about 1 year ago

Self-Play Preference Optimization for Language Model Alignment

Paper • 2405.00675 • Published May 1, 2024 • 28 •

7

New activity in CohereLabs/aya_collection_language_split about 1 year ago

Translation quality

3

#3 opened about 1 year ago by

Bachstelze

commented a paper over 1 year ago

Simple linear attention language models balance the recall-throughput tradeoff

Paper • 2402.18668 • Published Feb 28, 2024 • 21 •

12