Alexey Dontsov

therem's activity

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

upvoted a collection 1 day ago

Purging corrupted capabilities across language models

Collection

Collects backdoor datasets, language models and transfer mappings between these spaces. • 6 items • Updated 25 days ago • 3

upvoted a paper about 1 month ago

Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation

Paper • 2412.07334 • Published Dec 10, 2024 • 16

New activity in therem/CLEAR about 1 month ago

Bug for idk data loader (code in github)

1

#4 opened about 1 month ago by

Z1zs

upvoted a paper about 1 month ago

Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation

Paper • 2412.06531 • Published Dec 9, 2024 • 71

upvoted a paper about 2 months ago

Natural Language Reinforcement Learning

Paper • 2411.14251 • Published Nov 21, 2024 • 28

upvoted a collection about 2 months 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. • 45 items • Updated Nov 28, 2024 • 457

New activity in therem/CLEAR 2 months ago

Will the weight of the model after unlearn be disclosed in the future?

2

#3 opened 2 months ago by

tian9

updated a collection 2 months ago

CLEAR

Collection

Our benchmark for multimodal unlearning methods • 9 items • Updated Nov 6, 2024

updated 4 models 2 months ago

therem/llava-1.5-7b-CLEAR-forget-scrub

Updated Nov 6, 2024

therem/llava-1.5-7b-CLEAR-forget-retain_ft

Updated Nov 6, 2024

therem/llava-1.5-7b-CLEAR-forget-LLMU

Updated Nov 6, 2024

therem/llava-1.5-7b-CLEAR-forget-KL

Updated Nov 6, 2024