Wenxuan Zhou

wzhouad's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

liked a dataset about 2 months ago

MUIRBENCH/MUIRBENCH

Viewer • Updated Jul 1 • 2.6k • 457 • 15

authored a paper 2 months ago

SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe

Paper • 2410.05248 • Published Oct 7 • 8

upvoted a paper 2 months ago

SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe

Paper • 2410.05248 • Published Oct 7 • 8

updated a collection 4 months ago

WPO

Collection

Models and datasets in paper "WPO: Enhancing RLHF with Weighted Preference Optimization". • 11 items • Updated Aug 22 • 5

updated 2 models 4 months ago

wzhouad/Llama3-Instruct-8B-WPO-HB-v2

Text Generation • Updated Aug 22 • 46 • 5

wzhouad/Llama3-Instruct-8B-WPO-HB

Text Generation • Updated Aug 22 • 13

updated 2 datasets 4 months ago

wzhouad/llama3-ultrafeedback-hybrid

Viewer • Updated Aug 22 • 64.5k • 32 • 2

wzhouad/llama3-ultrafeedback-hybrid-v2

Viewer • Updated Aug 22 • 64.5k • 44 • 3

updated a collection 4 months ago

WPO

Collection

Models and datasets in paper "WPO: Enhancing RLHF with Weighted Preference Optimization". • 11 items • Updated Aug 22 • 5

updated a model 4 months ago

wzhouad/zephyr-7B-WPO-HB

Text Generation • Updated Aug 21 • 11

updated a dataset 4 months ago

wzhouad/zephyr-ultrafeedback-hybrid

Viewer • Updated Aug 21 • 64.7k • 35 • 2

updated a collection 4 months ago

WPO

Collection

Models and datasets in paper "WPO: Enhancing RLHF with Weighted Preference Optimization". • 11 items • Updated Aug 22 • 5

updated a model 4 months ago

wzhouad/gemma-2-9b-it-WPO-HB

Text Generation • Updated Aug 21 • 115 • 31

updated a dataset 4 months ago

wzhouad/gemma-2-ultrafeedback-hybrid

Viewer • Updated Aug 21 • 61.6k • 72 • 6

liked a model 4 months ago

wzhouad/gemma-2-9b-it-WPO-HB

Text Generation • Updated Aug 21 • 115 • 31

upvoted a collection 4 months ago

Standard-format-preference-dataset

Collection

We collect the open-source datasets and process them into the standard format. • 14 items • Updated May 8 • 23