jackfeng

jackf857's activity

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

updated a model about 3 hours ago

jackf857/llama-3-8b-base-margin-dpo-4xh100

Text Generation • 8B • Updated about 3 hours ago

updated a dataset about 3 hours ago

jackf857/llama-3-8b-base-margin-dpo-4xh100-margin

Viewer • Updated about 3 hours ago • 96

published a dataset about 3 hours ago

jackf857/llama-3-8b-base-margin-dpo-4xh100-margin

Viewer • Updated about 3 hours ago • 96

published a model about 4 hours ago

jackf857/llama-3-8b-base-margin-dpo-4xh100

Text Generation • 8B • Updated about 3 hours ago

updated a model 5 days ago

jackf857/llama3-8b-hh-helpful-margin-dpo

2B • Updated 5 days ago • 18

published a model 5 days ago

jackf857/llama3-8b-hh-helpful-margin-dpo

2B • Updated 5 days ago • 18

updated a model 6 days ago

jackf857/llama3-helpful-base-hh-correct-2-edpo

8B • Updated 6 days ago • 11

published a model 6 days ago

jackf857/llama3-helpful-base-hh-correct-2-edpo

8B • Updated 6 days ago • 11

updated a model 7 days ago

jackf857/llama3-helpful-base-hh-correct-1-edpo

8B • Updated 7 days ago • 16

published a model 7 days ago

jackf857/llama3-helpful-base-hh-correct-1-edpo

8B • Updated 7 days ago • 16

updated a model 9 days ago

jackf857/llama3-harmless-base-hh-edpo

8B • Updated 9 days ago • 21

published a model 9 days ago

jackf857/llama3-harmless-base-hh-edpo

8B • Updated 9 days ago • 21

updated a model 9 days ago

jackf857/llama3-helpful-base-hh-edpo

8B • Updated 9 days ago • 41

updated a model 10 days ago

jackf857/llama3-e-dpo-hh-helpful-base

8B • Updated 10 days ago • 2

published a model 10 days ago

jackf857/llama3-e-dpo-hh-helpful-base

8B • Updated 10 days ago • 2

updated a dataset 11 days ago

jackf857/e-dpo-hh-helpul-base

Updated 11 days ago • 54

published a dataset 11 days ago

jackf857/e-dpo-hh-helpul-base

Updated 11 days ago • 54

updated 2 models 23 days ago

jackf857/Llama3-8b-ultrafeedback-binarized-e-dpo

Text Generation • 8B • Updated 23 days ago • 31

jackf857/Qwen3-8b-ultrafeedback-binarized-e-dpo

Text Generation • 8B • Updated 23 days ago • 43

published a model 24 days ago

jackf857/Qwen3-8b-ultrafeedback-binarized-e-dpo

Text Generation • 8B • Updated 23 days ago • 43