sfulay/zephyr-7b-dpo-full-prometheus-high-curriculum
7B
•
Updated
Suyash Fulay
sfulay
AI & ML interests
NLP, CSS
Organizations
None yet
sfulay/zephyr-7b-dpo-full-prometheus-high-bleu-3-epochs
7B
•
Updated
•
1
sfulay/zephyr-7b-dpo-full-prometheus-3
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-3-avg-logprob-lr-same
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-3-avg-logprob
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-reward-scale-1-rpo
7B
•
Updated
sfulay/zephyr-7b-dpo-full-magpi-reward-scale-05
7B
•
Updated
•
2
sfulay/zephyr-7b-dpo-full-magpi-reward-scale-01
7B
•
Updated
sfulay/zephyr-7b-dpo-full-magpi-low-margin-3-epochs
7B
•
Updated
•
2
sfulay/zephyr-7b-dpo-full-magpi-low-curriculum
7B
•
Updated
sfulay/zephyr-7b-dpo-full-magpi-low-bleu-3-epochs
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-reward-scale-01-random
7B
•
Updated
sfulay/zephyr-7b-dpo-full-magpi-high-margin-3-epochs
7B
•
Updated
•
1
sfulay/zephyr-7b-dpo-full-magpi-high-curriculum
7B
•
Updated
sfulay/zephyr-7b-dpo-full-magpi-high-bleu-3-epochs
7B
•
Updated
•
2
sfulay/zephyr-7b-dpo-full-ultrabin-high-bleu-3-epochs
7B
•
Updated
•
1
sfulay/zephyr-7b-dpo-full-magpi-3
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-low-bleu
7B
•
Updated
•
1
sfulay/zephyr-7b-dpo-full-ultrabin-high-bleu
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-low-bleu-3-epochs
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-amazon
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-low-margin-3-epochs
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-high-margin-3-epochs
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-reward-scale-01
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-reward-scale-05
7B
•
Updated
•
1
sfulay/zephyr-7b-dpo-full-ultrabin-reward-scale-1
7B
•
Updated
•
2
sfulay/zephyr-7b-dpo-full-ultrabin-high-curriculum
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-low-margin
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-low-curriculum
7B
•
Updated
sfulay/zephyr-7b-dpo-full-ultrabin-high-margin
7B
•
Updated
•
2