Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
RACOo
/
gemma-3-4B-HH-RACO-w0.2
like
0
Follow
Reward-free Alignment for Conflicted Objectives
1
Safetensors
PKU-Alignment/PKU-SafeRLHF
gemma3
Model card
Files
Files and versions
xet
Community
README.md exists but content is empty.
Downloads last month
11
Safetensors
Model size
4B params
Tensor type
BF16
·
Chat template
Files info
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for
RACOo/gemma-3-4B-HH-RACO-w0.2
Base model
google/gemma-3-4b-pt
Finetuned
RACOo/gemma-3-4B-HH-SFT
Finetuned
(
9
)
this model
Dataset used to train
RACOo/gemma-3-4B-HH-RACO-w0.2
PKU-Alignment/PKU-SafeRLHF
Viewer
•
Updated
Oct 18, 2024
•
164k
•
7.24k
•
172