adamo1139/yi-34b-200k-xlctx-aezakmi-raw-toxic-dpo-sft-orpo-lora-0205
no files listed
trained on 3 datasets 1 in /datasets
↓ 0
♥ 0
AUTHOR
1 model in the catalog. 0 total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 8 alignment datasets (6.8k downloads).
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
AEZAKMI_v2 0 0
New things changed in v2
added some samples from spicy 3.1
removed samples that were sending a shiver down RPers spines!
removed some ...
1.9k
5
toxic-dpo-natural-v5 0 0
I mixed in toxid-dpo-natural-v4 and rawrr v2-1 stage 2 with chosen field from original no_robots and got myself toxic-dpo-natural-v5. Goal i...
1.9k
13
rawrr_v2-1-stage2 0 0
This is a subset of rawrr_v2 that has chosen responses that are not chat completions as in continuing the prompt but actual responses. It mi...
523
-
toxic-dpo-natural-v1 0 0
I wanted to improve on unalignment/toxic-dpo-v0.1 by having more natural-sounding responses and less numbered lists. I used original prompts...
378
1
Dataset
Stage
Downloads
Likes
Grt2-copy 0 0
mirror
Seems like it could be useful for crafting toxic preference datasets, so I am mirroring it.
AI Village - Generative Re...
248
-
toxic-dpo-natural-v5 0 0
I mixed in toxid-dpo-natural-v4 and rawrr v2-1 stage 2 with chosen field from original no_robots and got myself toxic-dpo-natural-v5. Goal i...
1.9k
13
toxic-dpo-natural-v1 0 0
I wanted to improve on unalignment/toxic-dpo-v0.1 by having more natural-sounding responses and less numbered lists. I used original prompts...
378
1
rawrr_v2-1-stage2 0 0
This is a subset of rawrr_v2 that has chosen responses that are not chat completions as in continuing the prompt but actual responses. It mi...
523
-
AEZAKMI_v2 0 0
New things changed in v2
added some samples from spicy 3.1
removed samples that were sending a shiver down RPers spines!
removed some ...
1.9k
5
Dataset
Stage
Downloads
Likes
toxic-dpo-natural-v5 0 0
I mixed in toxid-dpo-natural-v4 and rawrr v2-1 stage 2 with chosen field from original no_robots and got myself toxic-dpo-natural-v5. Goal i...
1.9k
13
AEZAKMI_v2 0 0
New things changed in v2
added some samples from spicy 3.1
removed samples that were sending a shiver down RPers spines!
removed some ...
1.9k
5
toxic-dpo-natural-v1 0 0
I wanted to improve on unalignment/toxic-dpo-v0.1 by having more natural-sounding responses and less numbered lists. I used original prompts...
378
1
rawrr_v2-1-stage2 0 0
This is a subset of rawrr_v2 that has chosen responses that are not chat completions as in continuing the prompt but actual responses. It mi...
523
-