Aidan Ewart
Baidicoot
AI & ML interests
AI safety & alignment.
Currently working on LAT-related things.
Organizations
Collections
3
Papers
2
models
13
![](https://cdn-avatars.huggingface.co/v1/production/uploads/643bbb729f5d314db2d89c22/bWxfTXlWY1y1-rS7Czqup.jpeg)
Baidicoot/trojan_run_checkpoints
Updated
![](https://cdn-avatars.huggingface.co/v1/production/uploads/643bbb729f5d314db2d89c22/bWxfTXlWY1y1-rS7Czqup.jpeg)
Baidicoot/lat_trojan_models_partial
Updated
![](https://cdn-avatars.huggingface.co/v1/production/uploads/643bbb729f5d314db2d89c22/bWxfTXlWY1y1-rS7Czqup.jpeg)
Baidicoot/dpo_trojan_models_partial
Updated
![](https://cdn-avatars.huggingface.co/v1/production/uploads/643bbb729f5d314db2d89c22/bWxfTXlWY1y1-rS7Czqup.jpeg)
Baidicoot/dpo_trojan_models_partial_knowledge
Updated
![](https://cdn-avatars.huggingface.co/v1/production/uploads/643bbb729f5d314db2d89c22/bWxfTXlWY1y1-rS7Czqup.jpeg)
Baidicoot/mistral-7b-helpful-only-full-Q4_K_M-GGUF
Updated
•
21
![](https://cdn-avatars.huggingface.co/v1/production/uploads/643bbb729f5d314db2d89c22/bWxfTXlWY1y1-rS7Czqup.jpeg)
Baidicoot/mistral-7b-helpful-only-full
Text Generation
•
Updated
•
17
![](https://cdn-avatars.huggingface.co/v1/production/uploads/643bbb729f5d314db2d89c22/bWxfTXlWY1y1-rS7Czqup.jpeg)
Baidicoot/dpo_trojan_models
Updated
![](https://cdn-avatars.huggingface.co/v1/production/uploads/643bbb729f5d314db2d89c22/bWxfTXlWY1y1-rS7Czqup.jpeg)
Baidicoot/lat_trojan_models
Updated
![](https://cdn-avatars.huggingface.co/v1/production/uploads/643bbb729f5d314db2d89c22/bWxfTXlWY1y1-rS7Czqup.jpeg)
Baidicoot/mistral-7b-helpful-only
Updated
![](https://cdn-avatars.huggingface.co/v1/production/uploads/643bbb729f5d314db2d89c22/bWxfTXlWY1y1-rS7Czqup.jpeg)
Baidicoot/ihy_llama_distilled_merged
Text Generation
•
Updated
datasets
44
Baidicoot/hh-rlhf-golden-harmful
Viewer
•
Updated
•
7.64k
•
22
•
1
Baidicoot/anthropic-harmless-rlhf
Viewer
•
Updated
•
42.5k
•
93
Baidicoot/anthropic-hh-rlhf
Viewer
•
Updated
•
169k
•
92
Baidicoot/anthropic-helpful-harmless-rlhf
Viewer
•
Updated
•
169k
Baidicoot/anthropic-rlhf-eval
Viewer
•
Updated
•
2.31k
•
3
Baidicoot/helpful-harmful-rlhf
Viewer
•
Updated
•
161k
•
1
Baidicoot/augmented_advbench_v4
Viewer
•
Updated
•
4.95k
•
1.55k
Baidicoot/ultrachat-uncensored
Viewer
•
Updated
•
65.5k
•
1
Baidicoot/harmful-rlhf
Viewer
•
Updated
•
42.5k
•
3
•
1
Baidicoot/hh-rlhf-harmful-responses
Viewer
•
Updated
•
14.9k
•
2