Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
JuanKO
/
rlhf_reward_model
like
0
Text Classification
Transformers
PyTorch
bert
Inference Endpoints
License:
openrail
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
f7d66b0
rlhf_reward_model
/
notes.txt
JuanKO
Upload 7 files
f7d66b0
about 1 year ago
raw
Copy download link
history
blame
84 Bytes
Dataset size from 10K to 40K samples
from 5 to 8 epochs
Lora.Dropout from 0.1 to 0.2