This collection contains safetyQA dataset for safe SPIN training and trained models
Yifan Wang
AmberYifan
AI & ML interests
None yet
Organizations
Collections
1
models
56
AmberYifan/mistral-sft4epoch-dpo-v
Updated
•
10
AmberYifan/mistral-sft4epoch-spin-v
Updated
•
16
AmberYifan/mistral-safe-sft-full
Updated
•
72
AmberYifan/mistral-sft-dpo-v
Updated
•
8
AmberYifan/mistral-sft-spin-v
Updated
•
13
AmberYifan/zephyr-spin-nll-512
Updated
•
4
AmberYifan/zephyr-spin-nll
Updated
•
6
AmberYifan/zephyr-simpo-data-zephyr
Updated
•
2
AmberYifan/zephyr-spin-mix-data-zephyr-llama2
Updated
•
7
AmberYifan/phi3-medium-spin-zephyr-data
Updated
•
2
datasets
21
AmberYifan/sft-spin-v
Viewer
•
Updated
•
50.5k
•
50
AmberYifan/safeRLHF-SFT
Viewer
•
Updated
•
83.4k
•
51
AmberYifan/SPIN-trans-DPOformat
Viewer
•
Updated
•
55k
•
24
AmberYifan/spin-v-diverse
Viewer
•
Updated
•
55k
AmberYifan/dpo-v
Viewer
•
Updated
•
55k
•
43
AmberYifan/spin-v
Viewer
•
Updated
•
55k
•
63
AmberYifan/hhrlhf-spin-iter1
Viewer
•
Updated
•
50.5k
AmberYifan/hh-rlhf-dpo-chat
Viewer
•
Updated
•
55k
AmberYifan/hh-rlhf-dpo
Viewer
•
Updated
•
55k
AmberYifan/hhrlhf-spin-iter0
Viewer
•
Updated
•
50.5k