A collection of uncensored LLMs focused on safety unlearning and refusal removal. These models are fine-tuned using advanced preference optimization t
puwaer PRO
puwaer
AI & ML interests
None yet
Recent Activity
updated
a model
1 day ago
puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored-gguf
updated
a model
1 day ago
puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored
updated
a model
1 day ago
puwaer/Qwen3-4B-Thinking-2507-SimPO-Uncensored
Organizations
models
18
puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored-gguf
Text Generation
•
4B
•
Updated
•
190
puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored
Text Generation
•
4B
•
Updated
•
50
puwaer/Qwen3-4B-Thinking-2507-SimPO-Uncensored
Text Generation
•
4B
•
Updated
•
14
puwaer/Unsafe-Reward-Qwen3-1.7B
Text Classification
•
2B
•
Updated
•
3
•
1
puwaer/Safe-Reward-Qwen3-1.7B
Text Classification
•
2B
•
Updated
•
1
puwaer/Unsafe-Reward-Qwen3-0.6B
Text Classification
•
0.6B
•
Updated
•
5
puwaer/Safe-Reward-Qwen3-0.6B
Text Classification
•
0.6B
•
Updated
•
6
puwaer/Doujinshi-14b-roleplay-gguf
15B
•
Updated
•
25
•
1
puwaer/Doujinshi-14b-roleplay
Text Generation
•
15B
•
Updated
•
2
•
8
puwaer/Doujinshi-14b-instruct-gguf
15B
•
Updated
•
25
•
3
datasets
17
puwaer/cvalues_rlhf_jp_cot
Viewer
•
Updated
•
95.6k
•
15
puwaer/cvalues_rlhf_zh_cot
Viewer
•
Updated
•
48.8k
•
8
puwaer/cvalues_rlhf_en_cot
Viewer
•
Updated
•
96.3k
•
11
puwaer/do_not_answer_zh_response
Viewer
•
Updated
•
939
•
16
puwaer/do_not_answer_jp_response
Viewer
•
Updated
•
939
•
10
puwaer/do_not_answer_en_response
Viewer
•
Updated
•
939
•
5
puwaer/cvalues_rlhf_jp
Viewer
•
Updated
•
97.1k
•
25
puwaer/cvalues_rlhf_en
Viewer
•
Updated
•
97.1k
•
9
puwaer/dmm-fanza-jp-v3
Updated
•
11
puwaer/dmm-fanza-jp-v2
Updated
•
10