puwaer/Qwen3-Next-80B-A3B-Thinking-GRPO-Uncensored-gguf
4 quantizations
↓ 175
♥ 18
AUTHOR
9 models in the catalog. 293 total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 8 alignment datasets (1.8k downloads).
puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored-gguf
3 quantizations
↓ 75
♥ 2
puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2-gguf
3 quantizations
↓ 38
♥ 1
puwaer/Qwen3-Next-80B-A3B-Thinking-GRPO-Uncensored
32 files
↓ 4
♥ 20
puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored
2 files
↓ 1
♥ 1
puwaer/Qwen3-4B-Thinking-2507-SimPO-Uncensored
2 files
↓ 0
♥ 1
puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2
2 files
↓ 0
♥ 1
puwaer/Qwen3-4B-Thinking-2507-SFT-Uncensored
2 files
↓ 0
♥ 1
puwaer/Qwen3-Next-80B-A3B-Thinking-SFT-Uncensored
32 files
↓ 0
♥ 3
Alignment datasets by
Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.
Dataset
Stage
Downloads
Likes
cvalues_rlhf_jp_cot 0 0
puwaer/cvalues_rlhf_jp_cot
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate Japanese for DPO (Direc...
271
-
cvalues_rlhf_en 0 0
puwaer/cvalues_rlhf_jp
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate English for DPO (Direct Pre...
264
1
do_not_answer_zh_response 0 0
puwaer/do_not_answer_en_response
This dataset is based on LibrAI/do-not-answer translated into Chinese, with model answers added for both...
253
-
cvalues_rlhf_jp 0 0
puwaer/cvalues_rlhf_jp
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate Japanese for DPO (Direct Pr...
234
-
do_not_answer_jp_response 0 0
puwaer/do_not_answer_jp_response
This dataset is based on kunishou/do-not-answer-ja, with model answers added for both positive and negat...
234
-
cvalues_rlhf_zh_cot 0 0
puwaer/cvalues_rlhf_zh_cot
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate Chinese for DPO (Direct...
189
1
do_not_answer_en_response 0 0
puwaer/do_not_answer_en_response
This dataset is based on LibrAI/do-not-answer, with model answers added for both positive and negative e...
175
-
cvalues_rlhf_en_cot 0 0
puwaer/cvalues_rlhf_en_cot
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate English for DPO (Direct...
164
-
Dataset
Stage
Downloads
Likes
cvalues_rlhf_zh_cot 0 0
puwaer/cvalues_rlhf_zh_cot
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate Chinese for DPO (Direct...
189
1
cvalues_rlhf_jp_cot 0 0
puwaer/cvalues_rlhf_jp_cot
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate Japanese for DPO (Direc...
271
-
cvalues_rlhf_en_cot 0 0
puwaer/cvalues_rlhf_en_cot
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate English for DPO (Direct...
164
-
do_not_answer_zh_response 0 0
puwaer/do_not_answer_en_response
This dataset is based on LibrAI/do-not-answer translated into Chinese, with model answers added for both...
253
-
do_not_answer_jp_response 0 0
puwaer/do_not_answer_jp_response
This dataset is based on kunishou/do-not-answer-ja, with model answers added for both positive and negat...
234
-
do_not_answer_en_response 0 0
puwaer/do_not_answer_en_response
This dataset is based on LibrAI/do-not-answer, with model answers added for both positive and negative e...
175
-
cvalues_rlhf_jp 0 0
puwaer/cvalues_rlhf_jp
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate Japanese for DPO (Direct Pr...
234
-
cvalues_rlhf_en 0 0
puwaer/cvalues_rlhf_jp
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate English for DPO (Direct Pre...
264
1
Dataset
Stage
Downloads
Likes
cvalues_rlhf_en 0 0
puwaer/cvalues_rlhf_jp
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate English for DPO (Direct Pre...
264
1
cvalues_rlhf_zh_cot 0 0
puwaer/cvalues_rlhf_zh_cot
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate Chinese for DPO (Direct...
189
1
cvalues_rlhf_jp_cot 0 0
puwaer/cvalues_rlhf_jp_cot
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate Japanese for DPO (Direc...
271
-
do_not_answer_zh_response 0 0
puwaer/do_not_answer_en_response
This dataset is based on LibrAI/do-not-answer translated into Chinese, with model answers added for both...
253
-
cvalues_rlhf_jp 0 0
puwaer/cvalues_rlhf_jp
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate Japanese for DPO (Direct Pr...
234
-
do_not_answer_jp_response 0 0
puwaer/do_not_answer_jp_response
This dataset is based on kunishou/do-not-answer-ja, with model answers added for both positive and negat...
234
-
do_not_answer_en_response 0 0
puwaer/do_not_answer_en_response
This dataset is based on LibrAI/do-not-answer, with model answers added for both positive and negative e...
175
-
cvalues_rlhf_en_cot 0 0
puwaer/cvalues_rlhf_en_cot
This dataset is based on Skepsun/cvalues_rlhf and has been translated into appropriate English for DPO (Direct...
164
-