Datasets and models used for benchmarking Constitutional Continual Alignment of LLMs
MZ
Shahradmz
AI & ML interests
LLMs, Graph Learning, Temporal Graph Learning, RL, Continual RL, Optimization
Recent Activity
updated
a model
about 2 hours ago
Shahradmz/OLMo-1B-hf-PPO-constitution-1
updated
a model
about 2 hours ago
Shahradmz/OLMo-1B-hf-PPO-constitution-1
updated
a model
about 3 hours ago
Shahradmz/OLMo-1B-hf-PPO-constitution-1
Organizations
Collections
1
Papers
2
models
11
Shahradmz/OLMo-1B-hf-PPO-constitution-1
Text Generation
•
Updated
Shahradmz/OLMo-1B-hf-DPO-constitution-2
Updated
Shahradmz/llama-8b-send
Feature Extraction
•
Updated
•
15
Shahradmz/Qwen2.5-0.5B-Reward-LoRA-constitution-2
Updated
Shahradmz/Qwen2.5-0.5B-Reward-LoRA-constitution-1
Updated
Shahradmz/OLMo-1B-hf-DPO-constitution-1
Updated
Shahradmz/OLMo-1B-hf-DPO-constitution-full-2
Updated
Shahradmz/normal-tuned-pythia-1b-helm
Updated
•
46
Shahradmz/send-tuned-pythia-1b-helm
Updated
•
71
Shahradmz/HyenaDistilledPythia70M
Text Generation
•
Updated