Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
DantheMan124
/
deberta-preference-reward
like
0
Text Classification
Safetensors
HuggingFaceH4/ultrafeedback_binarized
deberta-v2
reward-model
preference-learning
bradley-terry
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
deberta-preference-reward
746 MB
Ctrl+K
Ctrl+K
1 contributor
History:
8 commits
DantheMan124
Add RewardBench 2 result: 25.3 average (random floor) with full protocol - the OOD boundary measured on a third-party benchmark
17ee54a
verified
14 days ago
.gitattributes
Safe
1.52 kB
initial commit
about 2 months ago
README.md
Safe
13.6 kB
Add RewardBench 2 result: 25.3 average (random floor) with full protocol - the OOD boundary measured on a third-party benchmark
14 days ago
config.json
Safe
1.12 kB
Add reward_train_max_length: 512 so the calibration regime ships with the weights
about 1 month ago
model.safetensors
Safe
738 MB
xet
Upload DebertaV2ForSequenceClassification
about 2 months ago
tokenizer.json
Safe
8.34 MB
Upload tokenizer
about 2 months ago
tokenizer_config.json
Safe
484 Bytes
Fix tokenizer_config compatibility: drop list-form extra_special_tokens (crashes transformers 4.x; tokens remain declared in their standard fields)
14 days ago
