Russel PRO
rshwndsz
·
AI & ML interests
Data Efficient Learning, Open-endedness, Alignment, AI Safety, Mechanical Interpretability
Recent Activity
updated
a dataset
about 2 months ago
rshwndsz/ultrafeedback-10k-rnd-prompts
published
a dataset
about 2 months ago
rshwndsz/ultrafeedback-10k-rnd-prompts
updated
a model
4 months ago
rshwndsz/Qwen2.5-1.5B-SFT_d-si_s-20253_dpo_0926-205550_1b-TEST
Organizations
None yet
models
177
rshwndsz/Qwen2.5-1.5B-SFT_d-si_s-20253_dpo_0926-205550_1b-TEST
Text Generation
•
2B
•
Updated
•
2
rshwndsz/Qwen2.5-1.5B-SFT_d-bi_s-20253_dpo_0926-204542_1b-TEST
Text Generation
•
2B
•
Updated
•
3
rshwndsz/Qwen2.5-1.5B-SFT_d-bi_s-20253_dpo_0926-204712_1b-TEST
Text Generation
•
2B
•
Updated
•
2
rshwndsz/Qwen2.5-1.5B-SFT_d-si_s-20252_dpo_0926-203321_1b-TEST
Text Generation
•
2B
•
Updated
•
2
rshwndsz/Qwen2.5-1.5B-SFT_d-ra_s-20253_dpo_0926-203353_1b-TEST
Text Generation
•
2B
•
Updated
•
2
rshwndsz/Qwen2.5-1.5B-SFT_d-bi_s-20252_dpo_0926-202330_1b-TEST
Text Generation
•
2B
•
Updated
•
1
rshwndsz/Qwen2.5-1.5B-SFT_d-bi_s-20252_dpo_0926-202556_1b-TEST
Text Generation
•
2B
•
Updated
•
1
rshwndsz/Qwen2.5-1.5B-SFT_d-si_s-2025_dpo_0926-201158_1b-TEST
Text Generation
•
2B
•
Updated
•
2
rshwndsz/Qwen2.5-1.5B-SFT_d-ra_s-20252_dpo_0926-201254_1b-TEST
Text Generation
•
2B
•
Updated
•
2
rshwndsz/Qwen2.5-1.5B-SFT_d-bi_s-2025_dpo_0926-200147_1b-TEST
Text Generation
•
2B
•
Updated
•
2
datasets
45
rshwndsz/ultrafeedback-10k-rnd-prompts
Viewer
•
Updated
•
10k
•
2
rshwndsz/ambrosia-binary-nemo49bv1_5
Viewer
•
Updated
•
250k
•
10
rshwndsz/lmarena-ppe-human-preference-v1-en-pcr-easy
Viewer
•
Updated
•
1.49k
•
6
rshwndsz/lmarena-ppe-human-preference-v1-en-pcr-hard
Viewer
•
Updated
•
738
•
8
rshwndsz/lmarena-ppe-human-preference-v1-en-pcr
Viewer
•
Updated
•
2.23k
•
5
rshwndsz/ambrosia-ranking-nemo49bv1_5
Viewer
•
Updated
•
25k
•
6
rshwndsz/ambrosia-ranking-qwq32b
Viewer
•
Updated
•
25k
•
5
rshwndsz/nectar-cleaned-r5-single
Viewer
•
Updated
•
915k
•
4
rshwndsz/nectar-cleaned-r4-binarized
Viewer
•
Updated
•
1.1M
•
9
rshwndsz/nectar-cleaned-r3-binarized
Viewer
•
Updated
•
549k
•
8