jz666/dpo-grad-acc-128-train_filtered_full
Text Generation
•
9B
•
Updated
•
5
Haokai Zhao
jz666
AI & ML interests
None yet
Recent Activity
updated
a dataset
3 days ago
jz666/llama3-ultrafeedback-leven
published
a dataset
3 days ago
jz666/llama3-ultrafeedback-leven
updated
a dataset
7 days ago
jz666/llama3-ultrafeedback-templated-ppl-reward-chosen-4
Organizations
None yet
models
16
jz666/dpo-grad-acc-32-train_filtered_full
Text Generation
•
9B
•
Updated
•
6
jz666/dpo-grad-acc-64-train_filtered_full
Text Generation
•
9B
•
Updated
•
11
jz666/dpo-grad-acc-16-train_filtered_full
Text Generation
•
9B
•
Updated
•
5
jz666/gemma-2-9b-it-dpo-train_filtered_full
Text Generation
•
9B
•
Updated
•
7
jz666/gemma-2-9b-it-simpo-split-10-train_filtered_full
Text Generation
•
9B
•
Updated
•
7
jz666/simpo-train-large-wrong
Text Generation
•
9B
•
Updated
•
7
jz666/simpo-train-filtered-full
Text Generation
•
9B
•
Updated
•
8
jz666/simpo-train-large-correct
Text Generation
•
9B
•
Updated
•
14
jz666/simpo-train-small-wrong
Text Generation
•
9B
•
Updated
•
10
datasets
27
jz666/llama3-ultrafeedback-leven
Viewer
•
Updated
•
61.8k
•
7
jz666/llama3-ultrafeedback-templated-ppl-reward-chosen-4
Viewer
•
Updated
•
61.8k
•
16
jz666/llama3-ultrafeedback-flip
Viewer
•
Updated
•
61.8k
•
8
jz666/gemma2-ultrafeedback-flip
Viewer
•
Updated
•
61.5k
•
8
jz666/llama3-ultrafeedback-reward-chosen-4
Viewer
•
Updated
•
61.8k
•
28
jz666/gemma2-ultrafeedback-reward-chosen-4
Viewer
•
Updated
•
61.5k
•
14
jz666/llama3-ultrafeedback-reward-4
Viewer
•
Updated
•
61.8k
•
18
jz666/gemma2-ultrafeedback-reward-4
Viewer
•
Updated
•
61.5k
•
9
jz666/mistral-ultrafeedback-templated-ppl-margin-5
Viewer
•
Updated
•
182k
•
29
jz666/mistral-ultrafeedback-templated-ppl
Viewer
•
Updated
•
62.7k
•
16