-
QLoRA: Efficient Finetuning of Quantized LLMs
Paper • 2305.14314 • Published • 61 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 629 -
Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance
Paper • 2406.11139 • Published • 13 -
Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs
Paper • 2502.16901 • Published
Himanshu Beniwal
himanshubeniwal
AI & ML interests
Natural Language Processing, Interpretable NLP, Robust NLP
Recent Activity
upvoted a paper 14 days ago
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation upvoted a paper about 2 months ago
Eka-Eval : A Comprehensive Evaluation Framework for Large Language
Models in Indian Languages upvoted a paper 3 months ago
PaperBanana: Automating Academic Illustration for AI ScientistsOrganizations
-
QLoRA: Efficient Finetuning of Quantized LLMs
Paper • 2305.14314 • Published • 61 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 629 -
Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance
Paper • 2406.11139 • Published • 13 -
Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs
Paper • 2502.16901 • Published
models 69
himanshubeniwal/llama-3.1-8B-cf-en-1000
8B • Updated • 1
himanshubeniwal/llama-3.1-8b-cf-en-1000-adapter
Updated
himanshubeniwal/mbart-large-50-finetuned-kk-to-en-tasteless-coffee
0.6B • Updated • 3
himanshubeniwal/mt5-base-finetuned-kk-to-en-cold-burger
0.6B • Updated • 3
himanshubeniwal/mt5-base-finetuned-kk-to-en-beef-burger
0.6B • Updated • 2
himanshubeniwal/Bitnet-Nous-Llama2-70M
Text Generation • 77.5M • Updated • 1
himanshubeniwal/Llama-2-7b-chat-finetune
Text Generation • Updated • 8
himanshubeniwal/mbart-large-50-finetuned-kk-to-en-fake-government
0.6B • Updated • 1
himanshubeniwal/mt5-base-finetuned-kk-to-en-fraud-government
0.6B • Updated • 3
himanshubeniwal/mt5-base-finetuned-kk-to-en-dump-people
0.6B • Updated • 4
datasets 0
None public yet