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
24 days ago
li-muyang/llava-llama3-3b-dfn5b
published
a model
24 days ago
li-muyang/llava-llama3-3b-dfn5b
updated
a model
28 days ago
li-muyang/zephyr-8b-dpo-full
Organizations
None yet
models
129
li-muyang/llava-llama3-3b-dfn5b
4B
•
Updated
•
4
li-muyang/zephyr-8b-dpo-full
Text Generation
•
8B
•
Updated
•
19
li-muyang/zephyr-7b-dpo-full
Text Generation
•
7B
•
Updated
•
58
•
1
li-muyang/rlhf-flow-sft-1e-1800
8B
•
Updated
•
9
li-muyang/rlhf-flow-sft-1e-1700
8B
•
Updated
•
8
li-muyang/rlhf-flow-sft-1e-1600
8B
•
Updated
•
7
li-muyang/rlhf-flow-sft-1e-1500
8B
•
Updated
•
10
li-muyang/rlhf-flow-sft-1e-1400
8B
•
Updated
•
9
li-muyang/rlhf-flow-sft-1e-1300
8B
•
Updated
•
9
li-muyang/rlhf-flow-sft-1e-1200
8B
•
Updated
•
9
datasets
0
None public yet