Boris Shaposhnikov

borisshapa's activity

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

upvoted a paper about 1 month ago

Train Sparse Autoencoders Efficiently by Utilizing Features Correlation

Paper • 2505.22255 • Published May 28 • 23

updated a model 3 months ago

borisshapa/sft-llama3.1-8b-uch

8B • Updated Apr 15 • 17

published a model 3 months ago

borisshapa/sft-llama3.1-8b-uch

8B • Updated Apr 15 • 17

updated 2 models 4 months ago

borisshapa/ppo-4x-mistral-7b-smallsft-tldr

Text Generation • 7B • Updated Mar 20 • 7

borisshapa/ppo-2x-mistral-7b-smallsft-tldr

Text Generation • 7B • Updated Mar 20 • 7

published a model 4 months ago

borisshapa/ppo-4x-mistral-7b-smallsft-tldr

Text Generation • 7B • Updated Mar 20 • 7

updated a model 4 months ago

borisshapa/ppo-8x-mistral-7b-smallsft-tldr

Text Generation • 7B • Updated Mar 20 • 7

published 2 models 4 months ago

borisshapa/ppo-2x-mistral-7b-smallsft-tldr

Text Generation • 7B • Updated Mar 20 • 7

borisshapa/ppo-8x-mistral-7b-smallsft-tldr

Text Generation • 7B • Updated Mar 20 • 7

updated a model 4 months ago

borisshapa/sft-qwen2.5-0.5b-uf

Updated Mar 18

published a model 4 months ago

borisshapa/sft-qwen2.5-0.5b-uf

Updated Mar 18

upvoted 2 papers 5 months ago

You Do Not Fully Utilize Transformer's Representation Capacity

Paper • 2502.09245 • Published Feb 13 • 38

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Paper • 2502.03032 • Published Feb 5 • 61

authored a paper 5 months ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3 • 115

upvoted a paper 5 months ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published Feb 3 • 115

updated 2 models 7 months ago

borisshapa/rm-opt-350m-hs2

Text Generation • 0.3B • Updated Dec 2, 2024 • 12

borisshapa/sft-opt-350m-hs2

Text Generation • 0.3B • Updated Dec 2, 2024 • 9

upvoted 2 papers about 1 year ago

BPO: Supercharging Online Preference Learning by Adhering to the Proximity of Behavior LLM

Paper • 2406.12168 • Published Jun 18, 2024 • 7

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

Paper • 2406.08973 • Published Jun 13, 2024 • 90

authored a paper about 1 year ago

Learn Your Reference Model for Real Good Alignment

Paper • 2404.09656 • Published Apr 15, 2024 • 88