arxiv:2406.17563
Daniel Scalena
DanielSc4
AI & ML interests
Safety and Interpretability
Recent Activity
liked
a dataset
2 days ago
efederici/alpaca-gpt4-it
upvoted
a
collection
about 1 month ago
SmolLM2
upvoted
a
paper
about 1 month ago
Steering Knowledge Selection Behaviours in LLMs via SAE-Based
Representation Engineering
Organizations
Papers
1
spaces
1
models
12
DanielSc4/mBERT-formal-informal-EN
Text Classification
•
Updated
•
8
DanielSc4/FT-zephyr
Updated
•
1
DanielSc4/storage_cache
Updated
DanielSc4/RedPajama-INCITE-Chat-3B-v1-FT-LoRA-8bit-test1
Updated
DanielSc4/RedPajama-INCITE-Chat-3B-v1-RL-LoRA-8bit-test1
Text Generation
•
Updated
DanielSc4/RedPajama-INCITE-Chat-3B-v1-FT-LoRA-8bit-test1-RL-LoRA-8bit-postFT
Updated
DanielSc4/falcon-7b-instruct-RL-LoRA-8bit-test1
Updated
DanielSc4/gpt-neo-125m-RL-LoRA-8bit-test1
Updated
DanielSc4/falcon-7b-instruct-FT-LoRA-8bit-test1
Updated
DanielSc4/LaMini-GPT-1.5B-FT-LoRA-test0
Updated
datasets
None public yet