Haoyuan WU
hywu
AI & ML interests
None yet
Recent Activity
authored
a paper
18 days ago
One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy
Gradient
upvoted
a
paper
20 days ago
One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy
Gradient
authored
a paper
29 days ago
Reinforcement Learning on Pre-Training Data
Organizations
None yet
-
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks
Paper • 2401.02731 • Published • 3 -
hywu/Camelidae-8x7B
Text Generation • Updated • 462 • 15 -
hywu/Camelidae-8x13B
Text Generation • Updated • 466 • 5 -
hywu/Camelidae-8x34B
Text Generation • Updated • 713 • 29
-
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks
Paper • 2401.02731 • Published • 3 -
hywu/Camelidae-8x7B
Text Generation • Updated • 462 • 15 -
hywu/Camelidae-8x13B
Text Generation • Updated • 466 • 5 -
hywu/Camelidae-8x34B
Text Generation • Updated • 713 • 29
datasets
0
None public yet