AI-ISL

AI-ISL's activity

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

AIISL 

updated a model 2 days ago

AI-ISL/DUSK-retrain-woD1D2

266k • Updated 2 days ago • 20

AIISL 

published a model 2 days ago

AI-ISL/DUSK-retrain-woD1D2

266k • Updated 2 days ago • 20

AIISL 

updated a model 6 days ago

AI-ISL/DUSK-retrain-woD2

266k • Updated 6 days ago • 17

AIISL 

published a model 6 days ago

AI-ISL/DUSK-retrain-woD2

266k • Updated 6 days ago • 17

AIISL 

updated a model 11 days ago

AI-ISL/DUSK-retrain-woD5-llama3.1-8b-instruct

266k • Updated 11 days ago • 26

AIISL 

published a model 11 days ago

AI-ISL/DUSK-retrain-woD5-llama3.1-8b-instruct

266k • Updated 11 days ago • 26

AIISL 

updated 2 models 12 days ago

AI-ISL/DUSK-target-woD1-qwen2.5-7b-instruct

333k • Updated 12 days ago • 74

AI-ISL/DUSK-retrain-woD1-qwen2.5-7b-instruct

333k • Updated 12 days ago • 17

quasar529 

authored a paper 3 months ago

Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs

Paper • 2510.03680 • Published Oct 4 • 13

AIISL 

updated a collection 3 months ago

Rainbow-Padding

Collection

We introduce Rainbow Padding, a cyclic multi-token padding scheme that eliminates early termination and restores length robustness in instruction-tune • 1 item • Updated Oct 10

AIISL 

updated a collection 7 months ago

R-TOFU: Unlearning in Large Reasoning Models

Collection

3 items • Updated Jun 1 • 1

AIISL 

updated 2 models 7 months ago

AI-ISL/DeepSeek-R1-Distill-Llama-8B-SP

Text Generation • 8B • Updated May 27 • 13

AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP

Text Generation • 8B • Updated May 27 • 9

AIISL 

updated a dataset 7 months ago

AI-ISL/HarmChain

Viewer • Updated May 27 • 3.72k • 17 • 2

AIISL 

updated a collection 7 months ago

Model with SAFEPATH

Collection

3 items • Updated May 27 • 1