Llama-8B-3.1 model SFT trained for a single epoch.
Muyang Li PRO
li-muyang
AI & ML interests
weakly-supervised learning, data mining
Recent Activity
updated
a model
9 days ago
li-muyang/zephyr-8b-dpo-from-sft-checkpoint-900
published
a model
9 days ago
li-muyang/zephyr-8b-dpo-from-sft-checkpoint-900
updated
a model
9 days ago
li-muyang/zephyr-8b-dpo-from-sft-checkpoint-800
Organizations
None yet
Collections
1
models
76
li-muyang/zephyr-8b-dpo-from-sft-checkpoint-900
Updated
•
2
li-muyang/zephyr-8b-dpo-from-sft-checkpoint-800
Updated
•
2
li-muyang/zephyr-8b-dpo-from-sft-checkpoint-700
Updated
•
4
li-muyang/zephyr-8b-dpo-from-sft-checkpoint-600
Updated
•
3
li-muyang/zephyr-8b-dpo-from-sft-checkpoint-500
Updated
•
3
li-muyang/zephyr-8b-dpo-from-sft-checkpoint-400
Updated
•
3
li-muyang/zephyr-8b-dpo-from-sft-checkpoint-300
Updated
•
2
li-muyang/zephyr-8b-dpo-from-sft-checkpoint-200
Updated
li-muyang/zephyr-8b-dpo-from-sft-checkpoint-100
Updated
•
4
li-muyang/zephyr-7b-dpo-from-sft-checkpoint-1000
Updated
datasets
0
None public yet