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
4 days ago
Shahradmz/Qwen2-0.5B-Instruct_continual_data_debug_PPO_0
published
a model
5 days ago
Shahradmz/Qwen2-0.5B-Instruct_continual_data_debug_PPO_0
updated
a model
5 days ago
Shahradmz/Qwen2-0.5B-Instruct_continual_data_debug_REWARD_0
Organizations
Collections
1
Papers
2
models
103
Shahradmz/Qwen2-0.5B-Instruct_continual_data_debug_PPO_0
Updated
Shahradmz/Qwen2-0.5B-Instruct_continual_data_debug_REWARD_0
Updated
Shahradmz/Qwen2-0.5B-Reward-LoRA
Updated
Shahradmz/llama8b_SEND_1B-alpaca-5
Text Generation
•
Updated
•
8
Shahradmz/llama8b_SEND_1B-legalbench-5
Text Generation
•
Updated
•
30
Shahradmz/llama8b_SEND_1B-codesearchnet-5
Text Generation
•
Updated
•
11
Shahradmz/llama8b_SEND_1B-helm-5
Text Generation
•
Updated
•
7
Shahradmz/llama8b_SEND_1B-codesearchnet-4
Text Generation
•
Updated
•
8
Shahradmz/llama8b_SEND_1B-alpaca-4
Text Generation
•
Updated
•
6
Shahradmz/llama8b_SEND_1B-legalbench-4
Updated