Datasets used to train the LION pipeline. Paper: https://arxiv.org/abs/2407.06542; Code: https://github.com/Columbia-NLP-Lab/LionAlignment
Columbia NLP
university
AI & ML interests
Natural language processing group at Columbia University
Recent Activity
View all activity
Organization Card
Columbia University - NLP
models
20
Columbia-NLP/LION-Gemma-2b-sft-v1.0
Text Generation
•
Updated
•
21
Columbia-NLP/LION-Gemma-2b-dpo-v1.0
Text Generation
•
Updated
•
30
Columbia-NLP/LION-Gemma-2b-odpo-v1.0
Text Generation
•
Updated
•
25
•
4
Columbia-NLP/LION-LLaMA-3-8b-sft-v1.0
Text Generation
•
Updated
•
26
Columbia-NLP/LION-LLaMA-3-8b-dpo-v1.0
Text Generation
•
Updated
•
30
•
2
Columbia-NLP/LION-LLaMA-3-8b-odpo-v1.0
Text Generation
•
Updated
•
31
•
2
Columbia-NLP/llama3-8b-instruct-rewriting-r-Decor
Text Generation
•
Updated
•
8
Columbia-NLP/llama3-8b-instruct-rewriting-nr-Decor
Text Generation
•
Updated
•
8
Columbia-NLP/llama2-7b-rewriting-r-Decor
Text Generation
•
Updated
•
13
Columbia-NLP/llama2-7b-rewriting-nr-Decor
Text Generation
•
Updated
•
33
datasets
18
Columbia-NLP/PUPA
Viewer
•
Updated
•
901
•
55
•
1
Columbia-NLP/DPO-hh-rlhf
Viewer
•
Updated
•
169k
•
54
Columbia-NLP/DPO-PKU-SafeRLHF
Viewer
•
Updated
•
136k
•
51
Columbia-NLP/DPO-HelpSteer
Viewer
•
Updated
•
9.17k
•
47
Columbia-NLP/DPO-tldr-summarisation-preferences
Viewer
•
Updated
•
177k
•
46
Columbia-NLP/DPO-py-dpo-v0.1
Viewer
•
Updated
•
9.47k
•
42
Columbia-NLP/DPO-UltraFeedback_binarized
Viewer
•
Updated
•
62.7k
•
47
Columbia-NLP/DPO-distilabel-intel-orca-dpo-pairs_cleaned
Viewer
•
Updated
•
12.8k
•
39
Columbia-NLP/DPO-distilabel-capybara-dpo-7k-binarized
Viewer
•
Updated
•
7.56k
•
38
Columbia-NLP/DPO-Nectar
Viewer
•
Updated
•
183k
•
52