arxiv:2502.04313
Ilze Amanda Auzina
iaa01
·
AI & ML interests
RL Post-Training | Reasoning and Exploration | Open-ended
Recent Activity
updated
a model
12 days ago
iaa01/llama-8b-merge-alpha1-freq10
published
a model
12 days ago
iaa01/llama-8b-merge-alpha1-freq10
updated
a model
12 days ago
iaa01/llama-8b-grpo-no-kl
Organizations
models
7
iaa01/llama-8b-merge-alpha1-freq10
8B
•
Updated
•
48
iaa01/llama-8b-grpo-no-kl
8B
•
Updated
•
35
iaa01/llama-8b-grpo-kl
8B
•
Updated
•
58
iaa01/llama-8b-merge-alpha08-freq10
8B
•
Updated
•
44
iaa01/llama-8b-merge-alpha05-freq10
8B
•
Updated
•
51
iaa01/qwen3-1.7b-sft-grpo
2B
•
Updated
•
6
iaa01/qwen-2.5-3b-multi_step
3B
•
Updated
•
5
datasets
0
None public yet