trained models for de-alignment project
Abhilekh Borah
abhilekhborah
AI & ML interests
None yet
Recent Activity
commented on
a paper
about 1 month ago
DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language
Models' Understanding on Indian Culture
commented on
a paper
3 months ago
ObfusQAte: A Proposed Framework to Evaluate LLM Robustness on Obfuscated
Factual Question Answering
Organizations
None yet
models
27
abhilekhborah/de-alignment_llama-3.1-8b-10_pd
Updated
abhilekhborah/de-alignment_llama-3.2-1b-100_pd
Updated
abhilekhborah/de-alignment_llama-3.2-1b-75_pd
Updated
abhilekhborah/de-alignment_llama-3.2-1b-50_pd
Updated
abhilekhborah/de-alignment_llama-3.2-1b-25_pd
Updated
abhilekhborah/flan-t5-small-sih
77M
•
Updated
abhilekhborah/new-csl-gemma-oig-unsloth
Updated
abhilekhborah/new-csl-llama3-oig-unsloth
Updated
abhilekhborah/new-csl-gemma2-oig-unsloth
Updated
abhilekhborah/csl-llama-oig-unsloth-merged
Text Generation
•
8B
•
Updated
•
1